From 12c4d5c6b5bf9dd50d0601c36af4f99b65316d58 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Fri, 7 Oct 2022 23:22:22 +0300 Subject: [PATCH 01/50] hypernetwork training mk1 --- modules/hypernetwork.py | 88 ------ modules/hypernetwork/hypernetwork.py | 267 +++++++++++++++++++ modules/hypernetwork/ui.py | 43 +++ modules/sd_hijack.py | 4 +- modules/sd_hijack_optimizations.py | 3 +- modules/shared.py | 13 +- modules/textual_inversion/ui.py | 1 - modules/ui.py | 58 +++- scripts/xy_grid.py | 7 +- textual_inversion_templates/hypernetwork.txt | 27 ++ textual_inversion_templates/none.txt | 1 + webui.py | 9 + 12 files changed, 414 insertions(+), 107 deletions(-) delete mode 100644 modules/hypernetwork.py create mode 100644 modules/hypernetwork/hypernetwork.py create mode 100644 modules/hypernetwork/ui.py create mode 100644 textual_inversion_templates/hypernetwork.txt create mode 100644 textual_inversion_templates/none.txt diff --git a/modules/hypernetwork.py b/modules/hypernetwork.py deleted file mode 100644 index c7b8668..0000000 --- a/modules/hypernetwork.py +++ /dev/null @@ -1,88 +0,0 @@ -import glob -import os -import sys -import traceback - -import torch - -from ldm.util import default -from modules import devices, shared -import torch -from torch import einsum -from einops import rearrange, repeat - - -class HypernetworkModule(torch.nn.Module): - def __init__(self, dim, state_dict): - super().__init__() - - self.linear1 = torch.nn.Linear(dim, dim * 2) - self.linear2 = torch.nn.Linear(dim * 2, dim) - - self.load_state_dict(state_dict, strict=True) - self.to(devices.device) - - def forward(self, x): - return x + (self.linear2(self.linear1(x))) - - -class Hypernetwork: - filename = None - name = None - - def __init__(self, filename): - self.filename = filename - self.name = os.path.splitext(os.path.basename(filename))[0] - self.layers = {} - - state_dict = torch.load(filename, map_location='cpu') - for size, sd in state_dict.items(): - self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1])) - - -def load_hypernetworks(path): - res = {} - - for filename in glob.iglob(path + '**/*.pt', recursive=True): - try: - hn = Hypernetwork(filename) - res[hn.name] = hn - except Exception: - print(f"Error loading hypernetwork {filename}", file=sys.stderr) - print(traceback.format_exc(), file=sys.stderr) - - return res - - -def attention_CrossAttention_forward(self, x, context=None, mask=None): - h = self.heads - - q = self.to_q(x) - context = default(context, x) - - hypernetwork = shared.selected_hypernetwork() - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is not None: - k = self.to_k(hypernetwork_layers[0](context)) - v = self.to_v(hypernetwork_layers[1](context)) - else: - k = self.to_k(context) - v = self.to_v(context) - - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) - - sim = einsum('b i d, b j d -> b i j', q, k) * self.scale - - if mask is not None: - mask = rearrange(mask, 'b ... -> b (...)') - max_neg_value = -torch.finfo(sim.dtype).max - mask = repeat(mask, 'b j -> (b h) () j', h=h) - sim.masked_fill_(~mask, max_neg_value) - - # attention, what we cannot get enough of - attn = sim.softmax(dim=-1) - - out = einsum('b i j, b j d -> b i d', attn, v) - out = rearrange(out, '(b h) n d -> b n (h d)', h=h) - return self.to_out(out) diff --git a/modules/hypernetwork/hypernetwork.py b/modules/hypernetwork/hypernetwork.py new file mode 100644 index 0000000..a3d6a47 --- /dev/null +++ b/modules/hypernetwork/hypernetwork.py @@ -0,0 +1,267 @@ +import datetime +import glob +import html +import os +import sys +import traceback +import tqdm + +import torch + +from ldm.util import default +from modules import devices, shared, processing, sd_models +import torch +from torch import einsum +from einops import rearrange, repeat +import modules.textual_inversion.dataset + + +class HypernetworkModule(torch.nn.Module): + def __init__(self, dim, state_dict=None): + super().__init__() + + self.linear1 = torch.nn.Linear(dim, dim * 2) + self.linear2 = torch.nn.Linear(dim * 2, dim) + + if state_dict is not None: + self.load_state_dict(state_dict, strict=True) + else: + self.linear1.weight.data.fill_(0.0001) + self.linear1.bias.data.fill_(0.0001) + self.linear2.weight.data.fill_(0.0001) + self.linear2.bias.data.fill_(0.0001) + + self.to(devices.device) + + def forward(self, x): + return x + (self.linear2(self.linear1(x))) + + +class Hypernetwork: + filename = None + name = None + + def __init__(self, name=None): + self.filename = None + self.name = name + self.layers = {} + self.step = 0 + self.sd_checkpoint = None + self.sd_checkpoint_name = None + + for size in [320, 640, 768, 1280]: + self.layers[size] = (HypernetworkModule(size), HypernetworkModule(size)) + + def weights(self): + res = [] + + for k, layers in self.layers.items(): + for layer in layers: + layer.train() + res += [layer.linear1.weight, layer.linear1.bias, layer.linear2.weight, layer.linear2.bias] + + return res + + def save(self, filename): + state_dict = {} + + for k, v in self.layers.items(): + state_dict[k] = (v[0].state_dict(), v[1].state_dict()) + + state_dict['step'] = self.step + state_dict['name'] = self.name + state_dict['sd_checkpoint'] = self.sd_checkpoint + state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name + + torch.save(state_dict, filename) + + def load(self, filename): + self.filename = filename + if self.name is None: + self.name = os.path.splitext(os.path.basename(filename))[0] + + state_dict = torch.load(filename, map_location='cpu') + + for size, sd in state_dict.items(): + if type(size) == int: + self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1])) + + self.name = state_dict.get('name', self.name) + self.step = state_dict.get('step', 0) + self.sd_checkpoint = state_dict.get('sd_checkpoint', None) + self.sd_checkpoint_name = state_dict.get('sd_checkpoint_name', None) + + +def load_hypernetworks(path): + res = {} + + for filename in glob.iglob(path + '**/*.pt', recursive=True): + try: + hn = Hypernetwork() + hn.load(filename) + res[hn.name] = hn + except Exception: + print(f"Error loading hypernetwork {filename}", file=sys.stderr) + print(traceback.format_exc(), file=sys.stderr) + + return res + + +def attention_CrossAttention_forward(self, x, context=None, mask=None): + h = self.heads + + q = self.to_q(x) + context = default(context, x) + + hypernetwork_layers = (shared.hypernetwork.layers if shared.hypernetwork is not None else {}).get(context.shape[2], None) + + if hypernetwork_layers is not None: + hypernetwork_k, hypernetwork_v = hypernetwork_layers + + self.hypernetwork_k = hypernetwork_k + self.hypernetwork_v = hypernetwork_v + + context_k = hypernetwork_k(context) + context_v = hypernetwork_v(context) + else: + context_k = context + context_v = context + + k = self.to_k(context_k) + v = self.to_v(context_v) + + q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) + + sim = einsum('b i d, b j d -> b i j', q, k) * self.scale + + if mask is not None: + mask = rearrange(mask, 'b ... -> b (...)') + max_neg_value = -torch.finfo(sim.dtype).max + mask = repeat(mask, 'b j -> (b h) () j', h=h) + sim.masked_fill_(~mask, max_neg_value) + + # attention, what we cannot get enough of + attn = sim.softmax(dim=-1) + + out = einsum('b i j, b j d -> b i d', attn, v) + out = rearrange(out, '(b h) n d -> b n (h d)', h=h) + return self.to_out(out) + + +def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt): + assert hypernetwork_name, 'embedding not selected' + + shared.hypernetwork = shared.hypernetworks[hypernetwork_name] + + shared.state.textinfo = "Initializing hypernetwork training..." + shared.state.job_count = steps + + filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt') + + log_directory = os.path.join(log_directory, datetime.datetime.now().strftime("%Y-%m-%d"), hypernetwork_name) + + if save_hypernetwork_every > 0: + hypernetwork_dir = os.path.join(log_directory, "hypernetworks") + os.makedirs(hypernetwork_dir, exist_ok=True) + else: + hypernetwork_dir = None + + if create_image_every > 0: + images_dir = os.path.join(log_directory, "images") + os.makedirs(images_dir, exist_ok=True) + else: + images_dir = None + + cond_model = shared.sd_model.cond_stage_model + + shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." + with torch.autocast("cuda"): + ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=512, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file) + + hypernetwork = shared.hypernetworks[hypernetwork_name] + weights = hypernetwork.weights() + for weight in weights: + weight.requires_grad = True + + optimizer = torch.optim.AdamW(weights, lr=learn_rate) + + losses = torch.zeros((32,)) + + last_saved_file = "" + last_saved_image = "" + + ititial_step = hypernetwork.step or 0 + if ititial_step > steps: + return hypernetwork, filename + + pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step) + for i, (x, text) in pbar: + hypernetwork.step = i + ititial_step + + if hypernetwork.step > steps: + break + + if shared.state.interrupted: + break + + with torch.autocast("cuda"): + c = cond_model([text]) + + x = x.to(devices.device) + loss = shared.sd_model(x.unsqueeze(0), c)[0] + del x + + losses[hypernetwork.step % losses.shape[0]] = loss.item() + + optimizer.zero_grad() + loss.backward() + optimizer.step() + + pbar.set_description(f"loss: {losses.mean():.7f}") + + if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0: + last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name}-{hypernetwork.step}.pt') + hypernetwork.save(last_saved_file) + + if hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0: + last_saved_image = os.path.join(images_dir, f'{hypernetwork_name}-{hypernetwork.step}.png') + + preview_text = text if preview_image_prompt == "" else preview_image_prompt + + p = processing.StableDiffusionProcessingTxt2Img( + sd_model=shared.sd_model, + prompt=preview_text, + steps=20, + do_not_save_grid=True, + do_not_save_samples=True, + ) + + processed = processing.process_images(p) + image = processed.images[0] + + shared.state.current_image = image + image.save(last_saved_image) + + last_saved_image += f", prompt: {preview_text}" + + shared.state.job_no = hypernetwork.step + + shared.state.textinfo = f""" +

+Loss: {losses.mean():.7f}
+Step: {hypernetwork.step}
+Last prompt: {html.escape(text)}
+Last saved embedding: {html.escape(last_saved_file)}
+Last saved image: {html.escape(last_saved_image)}
+

+""" + + checkpoint = sd_models.select_checkpoint() + + hypernetwork.sd_checkpoint = checkpoint.hash + hypernetwork.sd_checkpoint_name = checkpoint.model_name + hypernetwork.save(filename) + + return hypernetwork, filename + + diff --git a/modules/hypernetwork/ui.py b/modules/hypernetwork/ui.py new file mode 100644 index 0000000..525f978 --- /dev/null +++ b/modules/hypernetwork/ui.py @@ -0,0 +1,43 @@ +import html +import os + +import gradio as gr + +import modules.textual_inversion.textual_inversion +import modules.textual_inversion.preprocess +from modules import sd_hijack, shared + + +def create_hypernetwork(name): + fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") + assert not os.path.exists(fn), f"file {fn} already exists" + + hypernetwork = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) + hypernetwork.save(fn) + + shared.reload_hypernetworks() + shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None) + + return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", "" + + +def train_hypernetwork(*args): + + initial_hypernetwork = shared.hypernetwork + + try: + sd_hijack.undo_optimizations() + + hypernetwork, filename = modules.hypernetwork.hypernetwork.train_hypernetwork(*args) + + res = f""" +Training {'interrupted' if shared.state.interrupted else 'finished'} at {hypernetwork.step} steps. +Hypernetwork saved to {html.escape(filename)} +""" + return res, "" + except Exception: + raise + finally: + shared.hypernetwork = initial_hypernetwork + sd_hijack.apply_optimizations() + diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index d68f89c..ec8c9d4 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -8,7 +8,7 @@ from torch import einsum from torch.nn.functional import silu import modules.textual_inversion.textual_inversion -from modules import prompt_parser, devices, sd_hijack_optimizations, shared, hypernetwork +from modules import prompt_parser, devices, sd_hijack_optimizations, shared from modules.shared import opts, device, cmd_opts import ldm.modules.attention @@ -32,6 +32,8 @@ def apply_optimizations(): def undo_optimizations(): + from modules.hypernetwork import hypernetwork + ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index d9cca48..3f32e02 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -45,8 +45,7 @@ def split_cross_attention_forward(self, x, context=None, mask=None): q_in = self.to_q(x) context = default(context, x) - hypernetwork = shared.selected_hypernetwork() - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) + hypernetwork_layers = (shared.hypernetwork.layers if shared.hypernetwork is not None else {}).get(context.shape[2], None) if hypernetwork_layers is not None: k_in = self.to_k(hypernetwork_layers[0](context)) diff --git a/modules/shared.py b/modules/shared.py index 879d842..c5a893e 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -13,7 +13,7 @@ import modules.memmon import modules.sd_models import modules.styles import modules.devices as devices -from modules import sd_samplers, hypernetwork +from modules import sd_samplers from modules.paths import models_path, script_path, sd_path sd_model_file = os.path.join(script_path, 'model.ckpt') @@ -28,6 +28,7 @@ parser.add_argument("--no-half", action='store_true', help="do not switch the mo parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)") parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI") parser.add_argument("--embeddings-dir", type=str, default=os.path.join(script_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)") +parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory") parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui") parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage") parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage") @@ -76,11 +77,15 @@ parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram config_filename = cmd_opts.ui_settings_file -hypernetworks = hypernetwork.load_hypernetworks(os.path.join(models_path, 'hypernetworks')) + +def reload_hypernetworks(): + from modules.hypernetwork import hypernetwork + hypernetworks.clear() + hypernetworks.update(hypernetwork.load_hypernetworks(cmd_opts.hypernetwork_dir)) -def selected_hypernetwork(): - return hypernetworks.get(opts.sd_hypernetwork, None) +hypernetworks = {} +hypernetwork = None class State: diff --git a/modules/textual_inversion/ui.py b/modules/textual_inversion/ui.py index f19ac5e..c57de1f 100644 --- a/modules/textual_inversion/ui.py +++ b/modules/textual_inversion/ui.py @@ -22,7 +22,6 @@ def preprocess(*args): def train_embedding(*args): - try: sd_hijack.undo_optimizations() diff --git a/modules/ui.py b/modules/ui.py index 4f18126..051908c 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -37,6 +37,7 @@ import modules.generation_parameters_copypaste from modules import prompt_parser from modules.images import save_image import modules.textual_inversion.ui +import modules.hypernetwork.ui # this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the bowser will not show any UI mimetypes.init() @@ -965,6 +966,18 @@ def create_ui(wrap_gradio_gpu_call): with gr.Column(): create_embedding = gr.Button(value="Create", variant='primary') + with gr.Group(): + gr.HTML(value="

Create a new hypernetwork

") + + new_hypernetwork_name = gr.Textbox(label="Name") + + with gr.Row(): + with gr.Column(scale=3): + gr.HTML(value="") + + with gr.Column(): + create_hypernetwork = gr.Button(value="Create", variant='primary') + with gr.Group(): gr.HTML(value="

Preprocess images

") @@ -986,6 +999,7 @@ def create_ui(wrap_gradio_gpu_call): with gr.Group(): gr.HTML(value="

Train an embedding; must specify a directory with a set of 512x512 images

") train_embedding_name = gr.Dropdown(label='Embedding', choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())) + train_hypernetwork_name = gr.Dropdown(label='Hypernetwork', choices=[x for x in shared.hypernetworks.keys()]) learn_rate = gr.Number(label='Learning rate', value=5.0e-03) dataset_directory = gr.Textbox(label='Dataset directory', placeholder="Path to directory with input images") log_directory = gr.Textbox(label='Log directory', placeholder="Path to directory where to write outputs", value="textual_inversion") @@ -993,15 +1007,12 @@ def create_ui(wrap_gradio_gpu_call): steps = gr.Number(label='Max steps', value=100000, precision=0) create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0) save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0) + preview_image_prompt = gr.Textbox(label='Preview prompt', value="") with gr.Row(): - with gr.Column(scale=2): - gr.HTML(value="") - - with gr.Column(): - with gr.Row(): - interrupt_training = gr.Button(value="Interrupt") - train_embedding = gr.Button(value="Train", variant='primary') + interrupt_training = gr.Button(value="Interrupt") + train_hypernetwork = gr.Button(value="Train Hypernetwork", variant='primary') + train_embedding = gr.Button(value="Train Embedding", variant='primary') with gr.Column(): progressbar = gr.HTML(elem_id="ti_progressbar") @@ -1027,6 +1038,18 @@ def create_ui(wrap_gradio_gpu_call): ] ) + create_hypernetwork.click( + fn=modules.hypernetwork.ui.create_hypernetwork, + inputs=[ + new_hypernetwork_name, + ], + outputs=[ + train_hypernetwork_name, + ti_output, + ti_outcome, + ] + ) + run_preprocess.click( fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]), _js="start_training_textual_inversion", @@ -1062,12 +1085,33 @@ def create_ui(wrap_gradio_gpu_call): ] ) + train_hypernetwork.click( + fn=wrap_gradio_gpu_call(modules.hypernetwork.ui.train_hypernetwork, extra_outputs=[gr.update()]), + _js="start_training_textual_inversion", + inputs=[ + train_hypernetwork_name, + learn_rate, + dataset_directory, + log_directory, + steps, + create_image_every, + save_embedding_every, + template_file, + preview_image_prompt, + ], + outputs=[ + ti_output, + ti_outcome, + ] + ) + interrupt_training.click( fn=lambda: shared.state.interrupt(), inputs=[], outputs=[], ) + def create_setting_component(key): def fun(): return opts.data[key] if key in opts.data else opts.data_labels[key].default diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index c0c364d..5b504de 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -78,8 +78,7 @@ def apply_checkpoint(p, x, xs): def apply_hypernetwork(p, x, xs): - hn = shared.hypernetworks.get(x, None) - opts.data["sd_hypernetwork"] = hn.name if hn is not None else 'None' + shared.hypernetwork = shared.hypernetworks.get(x, None) def format_value_add_label(p, opt, x): @@ -199,7 +198,7 @@ class Script(scripts.Script): modules.processing.fix_seed(p) p.batch_size = 1 - initial_hn = opts.sd_hypernetwork + initial_hn = shared.hypernetwork def process_axis(opt, vals): if opt.label == 'Nothing': @@ -308,6 +307,6 @@ class Script(scripts.Script): # restore checkpoint in case it was changed by axes modules.sd_models.reload_model_weights(shared.sd_model) - opts.data["sd_hypernetwork"] = initial_hn + shared.hypernetwork = initial_hn return processed diff --git a/textual_inversion_templates/hypernetwork.txt b/textual_inversion_templates/hypernetwork.txt new file mode 100644 index 0000000..91e0689 --- /dev/null +++ b/textual_inversion_templates/hypernetwork.txt @@ -0,0 +1,27 @@ +a photo of a [filewords] +a rendering of a [filewords] +a cropped photo of the [filewords] +the photo of a [filewords] +a photo of a clean [filewords] +a photo of a dirty [filewords] +a dark photo of the [filewords] +a photo of my [filewords] +a photo of the cool [filewords] +a close-up photo of a [filewords] +a bright photo of the [filewords] +a cropped photo of a [filewords] +a photo of the [filewords] +a good photo of the [filewords] +a photo of one [filewords] +a close-up photo of the [filewords] +a rendition of the [filewords] +a photo of the clean [filewords] +a rendition of a [filewords] +a photo of a nice [filewords] +a good photo of a [filewords] +a photo of the nice [filewords] +a photo of the small [filewords] +a photo of the weird [filewords] +a photo of the large [filewords] +a photo of a cool [filewords] +a photo of a small [filewords] diff --git a/textual_inversion_templates/none.txt b/textual_inversion_templates/none.txt new file mode 100644 index 0000000..f77af46 --- /dev/null +++ b/textual_inversion_templates/none.txt @@ -0,0 +1 @@ +picture diff --git a/webui.py b/webui.py index 480360f..60f9061 100644 --- a/webui.py +++ b/webui.py @@ -74,6 +74,15 @@ def wrap_gradio_gpu_call(func, extra_outputs=None): return modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs) +def set_hypernetwork(): + shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None) + + +shared.reload_hypernetworks() +shared.opts.onchange("sd_hypernetwork", set_hypernetwork) +set_hypernetwork() + + modules.scripts.load_scripts(os.path.join(script_path, "scripts")) shared.sd_model = modules.sd_models.load_model() From cc92dc1f8d73dd4d574c4c8ccab78b7fc61e440b Mon Sep 17 00:00:00 2001 From: ssysm Date: Sun, 9 Oct 2022 23:17:29 -0400 Subject: [PATCH 02/50] add vae path args --- modules/sd_models.py | 2 +- modules/shared.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/sd_models.py b/modules/sd_models.py index cb3982b..b697943 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -147,7 +147,7 @@ def load_model_weights(model, checkpoint_info): devices.dtype = torch.float32 if shared.cmd_opts.no_half else torch.float16 - vae_file = os.path.splitext(checkpoint_file)[0] + ".vae.pt" + vae_file = shared.cmd_opts.vae_path or os.path.splitext(checkpoint_file)[0] + ".vae.pt" if os.path.exists(vae_file): print(f"Loading VAE weights from: {vae_file}") vae_ckpt = torch.load(vae_file, map_location="cpu") diff --git a/modules/shared.py b/modules/shared.py index 2dc092d..52ccfa6 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -64,7 +64,7 @@ parser.add_argument("--autolaunch", action='store_true', help="open the webui UR parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False) parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False) parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False) - +parser.add_argument('--vae-path', type=str, help='Path to Variational Autoencoders model', default=None) cmd_opts = parser.parse_args() From f347ddfd808c56bb1bacdec0c4bedf826ff85cd8 Mon Sep 17 00:00:00 2001 From: RW21 Date: Mon, 10 Oct 2022 10:44:11 +0900 Subject: [PATCH 03/50] Remove max_batch_count from ui.py --- modules/ui.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/modules/ui.py b/modules/ui.py index 8c06ad7..8ba8491 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -524,7 +524,7 @@ def create_ui(wrap_gradio_gpu_call): denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7) with gr.Row(): - batch_count = gr.Slider(minimum=1, maximum=cmd_opts.max_batch_count, step=1, label='Batch count', value=1) + batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1) batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1) cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0) @@ -710,7 +710,7 @@ def create_ui(wrap_gradio_gpu_call): tiling = gr.Checkbox(label='Tiling', value=False) with gr.Row(): - batch_count = gr.Slider(minimum=1, maximum=cmd_opts.max_batch_count, step=1, label='Batch count', value=1) + batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1) batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1) with gr.Group(): From b340439586d844e76782149ca1857c8de35773ec Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Mon, 10 Oct 2022 05:28:06 +0100 Subject: [PATCH 04/50] Unlimited Token Works Unlimited tokens actually work now. Works with textual inversion too. Replaces the previous not-so-much-working implementation. --- modules/sd_hijack.py | 69 +++++++++++++++++++++++++++++--------------- 1 file changed, 46 insertions(+), 23 deletions(-) diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 437acce..8d5c77d 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -43,10 +43,7 @@ def undo_optimizations(): def get_target_prompt_token_count(token_count): - if token_count < 75: - return 75 - - return math.ceil(token_count / 10) * 10 + return math.ceil(max(token_count, 1) / 75) * 75 class StableDiffusionModelHijack: @@ -127,7 +124,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): self.token_mults[ident] = mult def tokenize_line(self, line, used_custom_terms, hijack_comments): - id_start = self.wrapped.tokenizer.bos_token_id id_end = self.wrapped.tokenizer.eos_token_id if opts.enable_emphasis: @@ -154,7 +150,8 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): i += 1 else: emb_len = int(embedding.vec.shape[0]) - fixes.append((len(remade_tokens), embedding)) + iteration = len(remade_tokens) // 75 + fixes.append((iteration, (len(remade_tokens) % 75, embedding))) remade_tokens += [0] * emb_len multipliers += [weight] * emb_len used_custom_terms.append((embedding.name, embedding.checksum())) @@ -162,10 +159,10 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): token_count = len(remade_tokens) prompt_target_length = get_target_prompt_token_count(token_count) - tokens_to_add = prompt_target_length - len(remade_tokens) + 1 + tokens_to_add = prompt_target_length - len(remade_tokens) - remade_tokens = [id_start] + remade_tokens + [id_end] * tokens_to_add - multipliers = [1.0] + multipliers + [1.0] * tokens_to_add + remade_tokens = remade_tokens + [id_end] * tokens_to_add + multipliers = multipliers + [1.0] * tokens_to_add return remade_tokens, fixes, multipliers, token_count @@ -260,29 +257,55 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): hijack_fixes.append(fixes) batch_multipliers.append(multipliers) return batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count - + def forward(self, text): - - if opts.use_old_emphasis_implementation: + use_old = opts.use_old_emphasis_implementation + if use_old: batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count = self.process_text_old(text) else: batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count = self.process_text(text) - self.hijack.fixes = hijack_fixes self.hijack.comments += hijack_comments if len(used_custom_terms) > 0: self.hijack.comments.append("Used embeddings: " + ", ".join([f'{word} [{checksum}]' for word, checksum in used_custom_terms])) + + if use_old: + self.hijack.fixes = hijack_fixes + return self.process_tokens(remade_batch_tokens, batch_multipliers) + + z = None + i = 0 + while max(map(len, remade_batch_tokens)) != 0: + rem_tokens = [x[75:] for x in remade_batch_tokens] + rem_multipliers = [x[75:] for x in batch_multipliers] + + self.hijack.fixes = [] + for unfiltered in hijack_fixes: + fixes = [] + for fix in unfiltered: + if fix[0] == i: + fixes.append(fix[1]) + self.hijack.fixes.append(fixes) + + z1 = self.process_tokens([x[:75] for x in remade_batch_tokens], [x[:75] for x in batch_multipliers]) + z = z1 if z is None else torch.cat((z, z1), axis=-2) + + remade_batch_tokens = rem_tokens + batch_multipliers = rem_multipliers + i += 1 + + return z + + + def process_tokens(self, remade_batch_tokens, batch_multipliers): + if not opts.use_old_emphasis_implementation: + remade_batch_tokens = [[self.wrapped.tokenizer.bos_token_id] + x[:75] + [self.wrapped.tokenizer.eos_token_id] for x in remade_batch_tokens] + batch_multipliers = [[1.0] + x[:75] + [1.0] for x in batch_multipliers] + + tokens = torch.asarray(remade_batch_tokens).to(device) + outputs = self.wrapped.transformer(input_ids=tokens) - target_token_count = get_target_prompt_token_count(token_count) + 2 - - position_ids_array = [min(x, 75) for x in range(target_token_count-1)] + [76] - position_ids = torch.asarray(position_ids_array, device=devices.device).expand((1, -1)) - - remade_batch_tokens_of_same_length = [x + [self.wrapped.tokenizer.eos_token_id] * (target_token_count - len(x)) for x in remade_batch_tokens] - tokens = torch.asarray(remade_batch_tokens_of_same_length).to(device) - - outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids, output_hidden_states=-opts.CLIP_stop_at_last_layers) if opts.CLIP_stop_at_last_layers > 1: z = outputs.hidden_states[-opts.CLIP_stop_at_last_layers] z = self.wrapped.transformer.text_model.final_layer_norm(z) @@ -290,7 +313,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): z = outputs.last_hidden_state # restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise - batch_multipliers_of_same_length = [x + [1.0] * (target_token_count - len(x)) for x in batch_multipliers] + batch_multipliers_of_same_length = [x + [1.0] * (75 - len(x)) for x in batch_multipliers] batch_multipliers = torch.asarray(batch_multipliers_of_same_length).to(device) original_mean = z.mean() z *= batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape) From 460bbae58726c177beddfcddf351f27e205d3fb2 Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Mon, 10 Oct 2022 16:09:06 +0100 Subject: [PATCH 05/50] Pad beginning of textual inversion embedding --- modules/sd_hijack.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 8d5c77d..3a60cd6 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -151,6 +151,11 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): else: emb_len = int(embedding.vec.shape[0]) iteration = len(remade_tokens) // 75 + if (len(remade_tokens) + emb_len) // 75 != iteration: + rem = (75 * (iteration + 1) - len(remade_tokens)) + remade_tokens += [id_end] * rem + multipliers += [1.0] * rem + iteration += 1 fixes.append((iteration, (len(remade_tokens) % 75, embedding))) remade_tokens += [0] * emb_len multipliers += [weight] * emb_len From d5c14365fd468dbf89fa12a68bea5b217077273c Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Mon, 10 Oct 2022 16:13:47 +0100 Subject: [PATCH 06/50] Add back in output hidden states parameter --- modules/sd_hijack.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 3a60cd6..3edc0e9 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -309,7 +309,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): batch_multipliers = [[1.0] + x[:75] + [1.0] for x in batch_multipliers] tokens = torch.asarray(remade_batch_tokens).to(device) - outputs = self.wrapped.transformer(input_ids=tokens) + outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers) if opts.CLIP_stop_at_last_layers > 1: z = outputs.hidden_states[-opts.CLIP_stop_at_last_layers] From 6c36fe5719a824fa18f6ad3e02727783f095bc5f Mon Sep 17 00:00:00 2001 From: Melan Date: Mon, 10 Oct 2022 18:16:04 +0200 Subject: [PATCH 07/50] Add ctrl+enter as a shortcut to quickly start a generation. --- script.js | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/script.js b/script.js index cf98960..a92c0f7 100644 --- a/script.js +++ b/script.js @@ -40,6 +40,22 @@ document.addEventListener("DOMContentLoaded", function() { mutationObserver.observe( gradioApp(), { childList:true, subtree:true }) }); +/** + * Add a ctrl+enter as a shortcut to start a generation + */ + document.addEventListener('keydown', function(e) { + var handled = false; + if (e.key !== undefined) { + if((e.key == "Enter" && (e.metaKey || e.ctrlKey))) handled = true; + } else if (e.keyCode !== undefined) { + if((e.keyCode == 13 && (e.metaKey || e.ctrlKey))) handled = true; + } + if (handled) { + gradioApp().querySelector("#txt2img_generate").click(); + e.preventDefault(); + } +}) + /** * checks that a UI element is not in another hidden element or tab content */ From 9d33baba587637815d818e5e641d8f8b74c4900d Mon Sep 17 00:00:00 2001 From: Vladimir Repin <32306715+mezotaken@users.noreply.github.com> Date: Mon, 10 Oct 2022 18:46:48 +0300 Subject: [PATCH 08/50] Always show previous mask and fix extras_send dest --- modules/ui.py | 2 +- style.css | 7 +++++++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/modules/ui.py b/modules/ui.py index 8ba8491..e8039d7 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -961,7 +961,7 @@ def create_ui(wrap_gradio_gpu_call): extras_send_to_inpaint.click( fn=lambda x: image_from_url_text(x), - _js="extract_image_from_gallery_img2img", + _js="extract_image_from_gallery_inpaint", inputs=[result_images], outputs=[init_img_with_mask], ) diff --git a/style.css b/style.css index 04bb957..00a3d07 100644 --- a/style.css +++ b/style.css @@ -467,3 +467,10 @@ input[type="range"]{ max-width: 32em; padding: 0; } + +canvas[key="mask"] { + z-index: 12 !important; + filter: invert(); + mix-blend-mode: multiply; + pointer-events: none; +} From b8c38f2bbfa28904f67f0c4f9cabab4d85ebced2 Mon Sep 17 00:00:00 2001 From: C43H66N12O12S2 <36072735+C43H66N12O12S2@users.noreply.github.com> Date: Mon, 10 Oct 2022 17:44:58 +0300 Subject: [PATCH 09/50] change prebuilt wheel --- launch.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/launch.py b/launch.py index f42f557..e1000f5 100644 --- a/launch.py +++ b/launch.py @@ -127,7 +127,7 @@ def prepare_enviroment(): if not is_installed("xformers") and xformers and platform.python_version().startswith("3.10"): if platform.system() == "Windows": - run_pip("install https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/a/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl", "xformers") + run_pip("install https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/c/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl", "xformers") elif platform.system() == "Linux": run_pip("install xformers", "xformers") From 623251ce2b8d152e242011f62984a8247a14a389 Mon Sep 17 00:00:00 2001 From: C43H66N12O12S2 <36072735+C43H66N12O12S2@users.noreply.github.com> Date: Mon, 10 Oct 2022 17:45:38 +0300 Subject: [PATCH 10/50] allow pascal onwards --- modules/sd_hijack.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 3edc0e9..827bf30 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -23,7 +23,7 @@ def apply_optimizations(): ldm.modules.diffusionmodules.model.nonlinearity = silu - if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and torch.cuda.get_device_capability(shared.device) == (8, 6)): + if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (8, 6)): print("Applying xformers cross attention optimization.") ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward From 3e7a981194ed9c454e951365846e4eba66fa7095 Mon Sep 17 00:00:00 2001 From: C43H66N12O12S2 <36072735+C43H66N12O12S2@users.noreply.github.com> Date: Mon, 10 Oct 2022 17:51:05 +0300 Subject: [PATCH 11/50] remove functorch --- modules/sd_hijack_optimizations.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 634fb4b..18408e6 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -13,8 +13,6 @@ from modules import shared if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers: try: import xformers.ops - import functorch - xformers._is_functorch_available = True shared.xformers_available = True except Exception: print("Cannot import xformers", file=sys.stderr) From 5c3254b3ee62ef46cb2e3a6ed14182efeb868f30 Mon Sep 17 00:00:00 2001 From: C43H66N12O12S2 <36072735+C43H66N12O12S2@users.noreply.github.com> Date: Mon, 10 Oct 2022 17:51:41 +0300 Subject: [PATCH 12/50] Update requirements.txt --- requirements.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 81641d6..631fe61 100644 --- a/requirements.txt +++ b/requirements.txt @@ -23,4 +23,3 @@ resize-right torchdiffeq kornia lark -functorch From e37d0cdd06772c8d6edb2272c0ef25c46c74cc6d Mon Sep 17 00:00:00 2001 From: C43H66N12O12S2 <36072735+C43H66N12O12S2@users.noreply.github.com> Date: Mon, 10 Oct 2022 17:51:53 +0300 Subject: [PATCH 13/50] Update requirements_versions.txt --- requirements_versions.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements_versions.txt b/requirements_versions.txt index fec3e9d..fdff268 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -22,4 +22,3 @@ resize-right==0.0.2 torchdiffeq==0.2.3 kornia==0.6.7 lark==1.1.2 -functorch==0.2.1 From ece27fe98933eb0eda8ea94dc496dd7554f3a08f Mon Sep 17 00:00:00 2001 From: C43H66N12O12S2 <36072735+C43H66N12O12S2@users.noreply.github.com> Date: Sun, 9 Oct 2022 18:55:33 +0300 Subject: [PATCH 14/50] Add files via upload --- modules/swinir_model_arch_v2.py | 1017 +++++++++++++++++++++++++++++++ 1 file changed, 1017 insertions(+) create mode 100644 modules/swinir_model_arch_v2.py diff --git a/modules/swinir_model_arch_v2.py b/modules/swinir_model_arch_v2.py new file mode 100644 index 0000000..0e28ae6 --- /dev/null +++ b/modules/swinir_model_arch_v2.py @@ -0,0 +1,1017 @@ +# ----------------------------------------------------------------------------------- +# Swin2SR: Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration, https://arxiv.org/abs/ +# Written by Conde and Choi et al. +# ----------------------------------------------------------------------------------- + +import math +import numpy as np +import torch +import torch.nn as nn +import torch.nn.functional as F +import torch.utils.checkpoint as checkpoint +from timm.models.layers import DropPath, to_2tuple, trunc_normal_ + + +class Mlp(nn.Module): + def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.): + super().__init__() + out_features = out_features or in_features + hidden_features = hidden_features or in_features + self.fc1 = nn.Linear(in_features, hidden_features) + self.act = act_layer() + self.fc2 = nn.Linear(hidden_features, out_features) + self.drop = nn.Dropout(drop) + + def forward(self, x): + x = self.fc1(x) + x = self.act(x) + x = self.drop(x) + x = self.fc2(x) + x = self.drop(x) + return x + + +def window_partition(x, window_size): + """ + Args: + x: (B, H, W, C) + window_size (int): window size + Returns: + windows: (num_windows*B, window_size, window_size, C) + """ + B, H, W, C = x.shape + x = x.view(B, H // window_size, window_size, W // window_size, window_size, C) + windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C) + return windows + + +def window_reverse(windows, window_size, H, W): + """ + Args: + windows: (num_windows*B, window_size, window_size, C) + window_size (int): Window size + H (int): Height of image + W (int): Width of image + Returns: + x: (B, H, W, C) + """ + B = int(windows.shape[0] / (H * W / window_size / window_size)) + x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1) + x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1) + return x + +class WindowAttention(nn.Module): + r""" Window based multi-head self attention (W-MSA) module with relative position bias. + It supports both of shifted and non-shifted window. + Args: + dim (int): Number of input channels. + window_size (tuple[int]): The height and width of the window. + num_heads (int): Number of attention heads. + qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True + attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0 + proj_drop (float, optional): Dropout ratio of output. Default: 0.0 + pretrained_window_size (tuple[int]): The height and width of the window in pre-training. + """ + + def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0., + pretrained_window_size=[0, 0]): + + super().__init__() + self.dim = dim + self.window_size = window_size # Wh, Ww + self.pretrained_window_size = pretrained_window_size + self.num_heads = num_heads + + self.logit_scale = nn.Parameter(torch.log(10 * torch.ones((num_heads, 1, 1))), requires_grad=True) + + # mlp to generate continuous relative position bias + self.cpb_mlp = nn.Sequential(nn.Linear(2, 512, bias=True), + nn.ReLU(inplace=True), + nn.Linear(512, num_heads, bias=False)) + + # get relative_coords_table + relative_coords_h = torch.arange(-(self.window_size[0] - 1), self.window_size[0], dtype=torch.float32) + relative_coords_w = torch.arange(-(self.window_size[1] - 1), self.window_size[1], dtype=torch.float32) + relative_coords_table = torch.stack( + torch.meshgrid([relative_coords_h, + relative_coords_w])).permute(1, 2, 0).contiguous().unsqueeze(0) # 1, 2*Wh-1, 2*Ww-1, 2 + if pretrained_window_size[0] > 0: + relative_coords_table[:, :, :, 0] /= (pretrained_window_size[0] - 1) + relative_coords_table[:, :, :, 1] /= (pretrained_window_size[1] - 1) + else: + relative_coords_table[:, :, :, 0] /= (self.window_size[0] - 1) + relative_coords_table[:, :, :, 1] /= (self.window_size[1] - 1) + relative_coords_table *= 8 # normalize to -8, 8 + relative_coords_table = torch.sign(relative_coords_table) * torch.log2( + torch.abs(relative_coords_table) + 1.0) / np.log2(8) + + self.register_buffer("relative_coords_table", relative_coords_table) + + # get pair-wise relative position index for each token inside the window + coords_h = torch.arange(self.window_size[0]) + coords_w = torch.arange(self.window_size[1]) + coords = torch.stack(torch.meshgrid([coords_h, coords_w])) # 2, Wh, Ww + coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww + relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, Wh*Ww, Wh*Ww + relative_coords = relative_coords.permute(1, 2, 0).contiguous() # Wh*Ww, Wh*Ww, 2 + relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0 + relative_coords[:, :, 1] += self.window_size[1] - 1 + relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1 + relative_position_index = relative_coords.sum(-1) # Wh*Ww, Wh*Ww + self.register_buffer("relative_position_index", relative_position_index) + + self.qkv = nn.Linear(dim, dim * 3, bias=False) + if qkv_bias: + self.q_bias = nn.Parameter(torch.zeros(dim)) + self.v_bias = nn.Parameter(torch.zeros(dim)) + else: + self.q_bias = None + self.v_bias = None + self.attn_drop = nn.Dropout(attn_drop) + self.proj = nn.Linear(dim, dim) + self.proj_drop = nn.Dropout(proj_drop) + self.softmax = nn.Softmax(dim=-1) + + def forward(self, x, mask=None): + """ + Args: + x: input features with shape of (num_windows*B, N, C) + mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None + """ + B_, N, C = x.shape + qkv_bias = None + if self.q_bias is not None: + qkv_bias = torch.cat((self.q_bias, torch.zeros_like(self.v_bias, requires_grad=False), self.v_bias)) + qkv = F.linear(input=x, weight=self.qkv.weight, bias=qkv_bias) + qkv = qkv.reshape(B_, N, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4) + q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple) + + # cosine attention + attn = (F.normalize(q, dim=-1) @ F.normalize(k, dim=-1).transpose(-2, -1)) + logit_scale = torch.clamp(self.logit_scale, max=torch.log(torch.tensor(1. / 0.01)).to(self.logit_scale.device)).exp() + attn = attn * logit_scale + + relative_position_bias_table = self.cpb_mlp(self.relative_coords_table).view(-1, self.num_heads) + relative_position_bias = relative_position_bias_table[self.relative_position_index.view(-1)].view( + self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1) # Wh*Ww,Wh*Ww,nH + relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww + relative_position_bias = 16 * torch.sigmoid(relative_position_bias) + attn = attn + relative_position_bias.unsqueeze(0) + + if mask is not None: + nW = mask.shape[0] + attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0) + attn = attn.view(-1, self.num_heads, N, N) + attn = self.softmax(attn) + else: + attn = self.softmax(attn) + + attn = self.attn_drop(attn) + + x = (attn @ v).transpose(1, 2).reshape(B_, N, C) + x = self.proj(x) + x = self.proj_drop(x) + return x + + def extra_repr(self) -> str: + return f'dim={self.dim}, window_size={self.window_size}, ' \ + f'pretrained_window_size={self.pretrained_window_size}, num_heads={self.num_heads}' + + def flops(self, N): + # calculate flops for 1 window with token length of N + flops = 0 + # qkv = self.qkv(x) + flops += N * self.dim * 3 * self.dim + # attn = (q @ k.transpose(-2, -1)) + flops += self.num_heads * N * (self.dim // self.num_heads) * N + # x = (attn @ v) + flops += self.num_heads * N * N * (self.dim // self.num_heads) + # x = self.proj(x) + flops += N * self.dim * self.dim + return flops + +class SwinTransformerBlock(nn.Module): + r""" Swin Transformer Block. + Args: + dim (int): Number of input channels. + input_resolution (tuple[int]): Input resulotion. + num_heads (int): Number of attention heads. + window_size (int): Window size. + shift_size (int): Shift size for SW-MSA. + mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. + qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True + drop (float, optional): Dropout rate. Default: 0.0 + attn_drop (float, optional): Attention dropout rate. Default: 0.0 + drop_path (float, optional): Stochastic depth rate. Default: 0.0 + act_layer (nn.Module, optional): Activation layer. Default: nn.GELU + norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm + pretrained_window_size (int): Window size in pre-training. + """ + + def __init__(self, dim, input_resolution, num_heads, window_size=7, shift_size=0, + mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0., + act_layer=nn.GELU, norm_layer=nn.LayerNorm, pretrained_window_size=0): + super().__init__() + self.dim = dim + self.input_resolution = input_resolution + self.num_heads = num_heads + self.window_size = window_size + self.shift_size = shift_size + self.mlp_ratio = mlp_ratio + if min(self.input_resolution) <= self.window_size: + # if window size is larger than input resolution, we don't partition windows + self.shift_size = 0 + self.window_size = min(self.input_resolution) + assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size" + + self.norm1 = norm_layer(dim) + self.attn = WindowAttention( + dim, window_size=to_2tuple(self.window_size), num_heads=num_heads, + qkv_bias=qkv_bias, attn_drop=attn_drop, proj_drop=drop, + pretrained_window_size=to_2tuple(pretrained_window_size)) + + self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity() + self.norm2 = norm_layer(dim) + mlp_hidden_dim = int(dim * mlp_ratio) + self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop) + + if self.shift_size > 0: + attn_mask = self.calculate_mask(self.input_resolution) + else: + attn_mask = None + + self.register_buffer("attn_mask", attn_mask) + + def calculate_mask(self, x_size): + # calculate attention mask for SW-MSA + H, W = x_size + img_mask = torch.zeros((1, H, W, 1)) # 1 H W 1 + h_slices = (slice(0, -self.window_size), + slice(-self.window_size, -self.shift_size), + slice(-self.shift_size, None)) + w_slices = (slice(0, -self.window_size), + slice(-self.window_size, -self.shift_size), + slice(-self.shift_size, None)) + cnt = 0 + for h in h_slices: + for w in w_slices: + img_mask[:, h, w, :] = cnt + cnt += 1 + + mask_windows = window_partition(img_mask, self.window_size) # nW, window_size, window_size, 1 + mask_windows = mask_windows.view(-1, self.window_size * self.window_size) + attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2) + attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0)) + + return attn_mask + + def forward(self, x, x_size): + H, W = x_size + B, L, C = x.shape + #assert L == H * W, "input feature has wrong size" + + shortcut = x + x = x.view(B, H, W, C) + + # cyclic shift + if self.shift_size > 0: + shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2)) + else: + shifted_x = x + + # partition windows + x_windows = window_partition(shifted_x, self.window_size) # nW*B, window_size, window_size, C + x_windows = x_windows.view(-1, self.window_size * self.window_size, C) # nW*B, window_size*window_size, C + + # W-MSA/SW-MSA (to be compatible for testing on images whose shapes are the multiple of window size + if self.input_resolution == x_size: + attn_windows = self.attn(x_windows, mask=self.attn_mask) # nW*B, window_size*window_size, C + else: + attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device)) + + # merge windows + attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C) + shifted_x = window_reverse(attn_windows, self.window_size, H, W) # B H' W' C + + # reverse cyclic shift + if self.shift_size > 0: + x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2)) + else: + x = shifted_x + x = x.view(B, H * W, C) + x = shortcut + self.drop_path(self.norm1(x)) + + # FFN + x = x + self.drop_path(self.norm2(self.mlp(x))) + + return x + + def extra_repr(self) -> str: + return f"dim={self.dim}, input_resolution={self.input_resolution}, num_heads={self.num_heads}, " \ + f"window_size={self.window_size}, shift_size={self.shift_size}, mlp_ratio={self.mlp_ratio}" + + def flops(self): + flops = 0 + H, W = self.input_resolution + # norm1 + flops += self.dim * H * W + # W-MSA/SW-MSA + nW = H * W / self.window_size / self.window_size + flops += nW * self.attn.flops(self.window_size * self.window_size) + # mlp + flops += 2 * H * W * self.dim * self.dim * self.mlp_ratio + # norm2 + flops += self.dim * H * W + return flops + +class PatchMerging(nn.Module): + r""" Patch Merging Layer. + Args: + input_resolution (tuple[int]): Resolution of input feature. + dim (int): Number of input channels. + norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm + """ + + def __init__(self, input_resolution, dim, norm_layer=nn.LayerNorm): + super().__init__() + self.input_resolution = input_resolution + self.dim = dim + self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False) + self.norm = norm_layer(2 * dim) + + def forward(self, x): + """ + x: B, H*W, C + """ + H, W = self.input_resolution + B, L, C = x.shape + assert L == H * W, "input feature has wrong size" + assert H % 2 == 0 and W % 2 == 0, f"x size ({H}*{W}) are not even." + + x = x.view(B, H, W, C) + + x0 = x[:, 0::2, 0::2, :] # B H/2 W/2 C + x1 = x[:, 1::2, 0::2, :] # B H/2 W/2 C + x2 = x[:, 0::2, 1::2, :] # B H/2 W/2 C + x3 = x[:, 1::2, 1::2, :] # B H/2 W/2 C + x = torch.cat([x0, x1, x2, x3], -1) # B H/2 W/2 4*C + x = x.view(B, -1, 4 * C) # B H/2*W/2 4*C + + x = self.reduction(x) + x = self.norm(x) + + return x + + def extra_repr(self) -> str: + return f"input_resolution={self.input_resolution}, dim={self.dim}" + + def flops(self): + H, W = self.input_resolution + flops = (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim + flops += H * W * self.dim // 2 + return flops + +class BasicLayer(nn.Module): + """ A basic Swin Transformer layer for one stage. + Args: + dim (int): Number of input channels. + input_resolution (tuple[int]): Input resolution. + depth (int): Number of blocks. + num_heads (int): Number of attention heads. + window_size (int): Local window size. + mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. + qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True + drop (float, optional): Dropout rate. Default: 0.0 + attn_drop (float, optional): Attention dropout rate. Default: 0.0 + drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0 + norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm + downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None + use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False. + pretrained_window_size (int): Local window size in pre-training. + """ + + def __init__(self, dim, input_resolution, depth, num_heads, window_size, + mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., + drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False, + pretrained_window_size=0): + + super().__init__() + self.dim = dim + self.input_resolution = input_resolution + self.depth = depth + self.use_checkpoint = use_checkpoint + + # build blocks + self.blocks = nn.ModuleList([ + SwinTransformerBlock(dim=dim, input_resolution=input_resolution, + num_heads=num_heads, window_size=window_size, + shift_size=0 if (i % 2 == 0) else window_size // 2, + mlp_ratio=mlp_ratio, + qkv_bias=qkv_bias, + drop=drop, attn_drop=attn_drop, + drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path, + norm_layer=norm_layer, + pretrained_window_size=pretrained_window_size) + for i in range(depth)]) + + # patch merging layer + if downsample is not None: + self.downsample = downsample(input_resolution, dim=dim, norm_layer=norm_layer) + else: + self.downsample = None + + def forward(self, x, x_size): + for blk in self.blocks: + if self.use_checkpoint: + x = checkpoint.checkpoint(blk, x, x_size) + else: + x = blk(x, x_size) + if self.downsample is not None: + x = self.downsample(x) + return x + + def extra_repr(self) -> str: + return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}" + + def flops(self): + flops = 0 + for blk in self.blocks: + flops += blk.flops() + if self.downsample is not None: + flops += self.downsample.flops() + return flops + + def _init_respostnorm(self): + for blk in self.blocks: + nn.init.constant_(blk.norm1.bias, 0) + nn.init.constant_(blk.norm1.weight, 0) + nn.init.constant_(blk.norm2.bias, 0) + nn.init.constant_(blk.norm2.weight, 0) + +class PatchEmbed(nn.Module): + r""" Image to Patch Embedding + Args: + img_size (int): Image size. Default: 224. + patch_size (int): Patch token size. Default: 4. + in_chans (int): Number of input image channels. Default: 3. + embed_dim (int): Number of linear projection output channels. Default: 96. + norm_layer (nn.Module, optional): Normalization layer. Default: None + """ + + def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None): + super().__init__() + img_size = to_2tuple(img_size) + patch_size = to_2tuple(patch_size) + patches_resolution = [img_size[0] // patch_size[0], img_size[1] // patch_size[1]] + self.img_size = img_size + self.patch_size = patch_size + self.patches_resolution = patches_resolution + self.num_patches = patches_resolution[0] * patches_resolution[1] + + self.in_chans = in_chans + self.embed_dim = embed_dim + + self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size) + if norm_layer is not None: + self.norm = norm_layer(embed_dim) + else: + self.norm = None + + def forward(self, x): + B, C, H, W = x.shape + # FIXME look at relaxing size constraints + # assert H == self.img_size[0] and W == self.img_size[1], + # f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})." + x = self.proj(x).flatten(2).transpose(1, 2) # B Ph*Pw C + if self.norm is not None: + x = self.norm(x) + return x + + def flops(self): + Ho, Wo = self.patches_resolution + flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1]) + if self.norm is not None: + flops += Ho * Wo * self.embed_dim + return flops + +class RSTB(nn.Module): + """Residual Swin Transformer Block (RSTB). + + Args: + dim (int): Number of input channels. + input_resolution (tuple[int]): Input resolution. + depth (int): Number of blocks. + num_heads (int): Number of attention heads. + window_size (int): Local window size. + mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. + qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True + drop (float, optional): Dropout rate. Default: 0.0 + attn_drop (float, optional): Attention dropout rate. Default: 0.0 + drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0 + norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm + downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None + use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False. + img_size: Input image size. + patch_size: Patch size. + resi_connection: The convolutional block before residual connection. + """ + + def __init__(self, dim, input_resolution, depth, num_heads, window_size, + mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., + drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False, + img_size=224, patch_size=4, resi_connection='1conv'): + super(RSTB, self).__init__() + + self.dim = dim + self.input_resolution = input_resolution + + self.residual_group = BasicLayer(dim=dim, + input_resolution=input_resolution, + depth=depth, + num_heads=num_heads, + window_size=window_size, + mlp_ratio=mlp_ratio, + qkv_bias=qkv_bias, + drop=drop, attn_drop=attn_drop, + drop_path=drop_path, + norm_layer=norm_layer, + downsample=downsample, + use_checkpoint=use_checkpoint) + + if resi_connection == '1conv': + self.conv = nn.Conv2d(dim, dim, 3, 1, 1) + elif resi_connection == '3conv': + # to save parameters and memory + self.conv = nn.Sequential(nn.Conv2d(dim, dim // 4, 3, 1, 1), nn.LeakyReLU(negative_slope=0.2, inplace=True), + nn.Conv2d(dim // 4, dim // 4, 1, 1, 0), + nn.LeakyReLU(negative_slope=0.2, inplace=True), + nn.Conv2d(dim // 4, dim, 3, 1, 1)) + + self.patch_embed = PatchEmbed( + img_size=img_size, patch_size=patch_size, in_chans=dim, embed_dim=dim, + norm_layer=None) + + self.patch_unembed = PatchUnEmbed( + img_size=img_size, patch_size=patch_size, in_chans=dim, embed_dim=dim, + norm_layer=None) + + def forward(self, x, x_size): + return self.patch_embed(self.conv(self.patch_unembed(self.residual_group(x, x_size), x_size))) + x + + def flops(self): + flops = 0 + flops += self.residual_group.flops() + H, W = self.input_resolution + flops += H * W * self.dim * self.dim * 9 + flops += self.patch_embed.flops() + flops += self.patch_unembed.flops() + + return flops + +class PatchUnEmbed(nn.Module): + r""" Image to Patch Unembedding + + Args: + img_size (int): Image size. Default: 224. + patch_size (int): Patch token size. Default: 4. + in_chans (int): Number of input image channels. Default: 3. + embed_dim (int): Number of linear projection output channels. Default: 96. + norm_layer (nn.Module, optional): Normalization layer. Default: None + """ + + def __init__(self, img_size=224, patch_size=4, in_chans=3, embed_dim=96, norm_layer=None): + super().__init__() + img_size = to_2tuple(img_size) + patch_size = to_2tuple(patch_size) + patches_resolution = [img_size[0] // patch_size[0], img_size[1] // patch_size[1]] + self.img_size = img_size + self.patch_size = patch_size + self.patches_resolution = patches_resolution + self.num_patches = patches_resolution[0] * patches_resolution[1] + + self.in_chans = in_chans + self.embed_dim = embed_dim + + def forward(self, x, x_size): + B, HW, C = x.shape + x = x.transpose(1, 2).view(B, self.embed_dim, x_size[0], x_size[1]) # B Ph*Pw C + return x + + def flops(self): + flops = 0 + return flops + + +class Upsample(nn.Sequential): + """Upsample module. + + Args: + scale (int): Scale factor. Supported scales: 2^n and 3. + num_feat (int): Channel number of intermediate features. + """ + + def __init__(self, scale, num_feat): + m = [] + if (scale & (scale - 1)) == 0: # scale = 2^n + for _ in range(int(math.log(scale, 2))): + m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1)) + m.append(nn.PixelShuffle(2)) + elif scale == 3: + m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1)) + m.append(nn.PixelShuffle(3)) + else: + raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.') + super(Upsample, self).__init__(*m) + +class Upsample_hf(nn.Sequential): + """Upsample module. + + Args: + scale (int): Scale factor. Supported scales: 2^n and 3. + num_feat (int): Channel number of intermediate features. + """ + + def __init__(self, scale, num_feat): + m = [] + if (scale & (scale - 1)) == 0: # scale = 2^n + for _ in range(int(math.log(scale, 2))): + m.append(nn.Conv2d(num_feat, 4 * num_feat, 3, 1, 1)) + m.append(nn.PixelShuffle(2)) + elif scale == 3: + m.append(nn.Conv2d(num_feat, 9 * num_feat, 3, 1, 1)) + m.append(nn.PixelShuffle(3)) + else: + raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.') + super(Upsample_hf, self).__init__(*m) + + +class UpsampleOneStep(nn.Sequential): + """UpsampleOneStep module (the difference with Upsample is that it always only has 1conv + 1pixelshuffle) + Used in lightweight SR to save parameters. + + Args: + scale (int): Scale factor. Supported scales: 2^n and 3. + num_feat (int): Channel number of intermediate features. + + """ + + def __init__(self, scale, num_feat, num_out_ch, input_resolution=None): + self.num_feat = num_feat + self.input_resolution = input_resolution + m = [] + m.append(nn.Conv2d(num_feat, (scale ** 2) * num_out_ch, 3, 1, 1)) + m.append(nn.PixelShuffle(scale)) + super(UpsampleOneStep, self).__init__(*m) + + def flops(self): + H, W = self.input_resolution + flops = H * W * self.num_feat * 3 * 9 + return flops + + + +class Swin2SR(nn.Module): + r""" Swin2SR + A PyTorch impl of : `Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration`. + + Args: + img_size (int | tuple(int)): Input image size. Default 64 + patch_size (int | tuple(int)): Patch size. Default: 1 + in_chans (int): Number of input image channels. Default: 3 + embed_dim (int): Patch embedding dimension. Default: 96 + depths (tuple(int)): Depth of each Swin Transformer layer. + num_heads (tuple(int)): Number of attention heads in different layers. + window_size (int): Window size. Default: 7 + mlp_ratio (float): Ratio of mlp hidden dim to embedding dim. Default: 4 + qkv_bias (bool): If True, add a learnable bias to query, key, value. Default: True + drop_rate (float): Dropout rate. Default: 0 + attn_drop_rate (float): Attention dropout rate. Default: 0 + drop_path_rate (float): Stochastic depth rate. Default: 0.1 + norm_layer (nn.Module): Normalization layer. Default: nn.LayerNorm. + ape (bool): If True, add absolute position embedding to the patch embedding. Default: False + patch_norm (bool): If True, add normalization after patch embedding. Default: True + use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False + upscale: Upscale factor. 2/3/4/8 for image SR, 1 for denoising and compress artifact reduction + img_range: Image range. 1. or 255. + upsampler: The reconstruction reconstruction module. 'pixelshuffle'/'pixelshuffledirect'/'nearest+conv'/None + resi_connection: The convolutional block before residual connection. '1conv'/'3conv' + """ + + def __init__(self, img_size=64, patch_size=1, in_chans=3, + embed_dim=96, depths=[6, 6, 6, 6], num_heads=[6, 6, 6, 6], + window_size=7, mlp_ratio=4., qkv_bias=True, + drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1, + norm_layer=nn.LayerNorm, ape=False, patch_norm=True, + use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv', + **kwargs): + super(Swin2SR, self).__init__() + num_in_ch = in_chans + num_out_ch = in_chans + num_feat = 64 + self.img_range = img_range + if in_chans == 3: + rgb_mean = (0.4488, 0.4371, 0.4040) + self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1) + else: + self.mean = torch.zeros(1, 1, 1, 1) + self.upscale = upscale + self.upsampler = upsampler + self.window_size = window_size + + ##################################################################################################### + ################################### 1, shallow feature extraction ################################### + self.conv_first = nn.Conv2d(num_in_ch, embed_dim, 3, 1, 1) + + ##################################################################################################### + ################################### 2, deep feature extraction ###################################### + self.num_layers = len(depths) + self.embed_dim = embed_dim + self.ape = ape + self.patch_norm = patch_norm + self.num_features = embed_dim + self.mlp_ratio = mlp_ratio + + # split image into non-overlapping patches + self.patch_embed = PatchEmbed( + img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim, + norm_layer=norm_layer if self.patch_norm else None) + num_patches = self.patch_embed.num_patches + patches_resolution = self.patch_embed.patches_resolution + self.patches_resolution = patches_resolution + + # merge non-overlapping patches into image + self.patch_unembed = PatchUnEmbed( + img_size=img_size, patch_size=patch_size, in_chans=embed_dim, embed_dim=embed_dim, + norm_layer=norm_layer if self.patch_norm else None) + + # absolute position embedding + if self.ape: + self.absolute_pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim)) + trunc_normal_(self.absolute_pos_embed, std=.02) + + self.pos_drop = nn.Dropout(p=drop_rate) + + # stochastic depth + dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))] # stochastic depth decay rule + + # build Residual Swin Transformer blocks (RSTB) + self.layers = nn.ModuleList() + for i_layer in range(self.num_layers): + layer = RSTB(dim=embed_dim, + input_resolution=(patches_resolution[0], + patches_resolution[1]), + depth=depths[i_layer], + num_heads=num_heads[i_layer], + window_size=window_size, + mlp_ratio=self.mlp_ratio, + qkv_bias=qkv_bias, + drop=drop_rate, attn_drop=attn_drop_rate, + drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results + norm_layer=norm_layer, + downsample=None, + use_checkpoint=use_checkpoint, + img_size=img_size, + patch_size=patch_size, + resi_connection=resi_connection + + ) + self.layers.append(layer) + + if self.upsampler == 'pixelshuffle_hf': + self.layers_hf = nn.ModuleList() + for i_layer in range(self.num_layers): + layer = RSTB(dim=embed_dim, + input_resolution=(patches_resolution[0], + patches_resolution[1]), + depth=depths[i_layer], + num_heads=num_heads[i_layer], + window_size=window_size, + mlp_ratio=self.mlp_ratio, + qkv_bias=qkv_bias, + drop=drop_rate, attn_drop=attn_drop_rate, + drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results + norm_layer=norm_layer, + downsample=None, + use_checkpoint=use_checkpoint, + img_size=img_size, + patch_size=patch_size, + resi_connection=resi_connection + + ) + self.layers_hf.append(layer) + + self.norm = norm_layer(self.num_features) + + # build the last conv layer in deep feature extraction + if resi_connection == '1conv': + self.conv_after_body = nn.Conv2d(embed_dim, embed_dim, 3, 1, 1) + elif resi_connection == '3conv': + # to save parameters and memory + self.conv_after_body = nn.Sequential(nn.Conv2d(embed_dim, embed_dim // 4, 3, 1, 1), + nn.LeakyReLU(negative_slope=0.2, inplace=True), + nn.Conv2d(embed_dim // 4, embed_dim // 4, 1, 1, 0), + nn.LeakyReLU(negative_slope=0.2, inplace=True), + nn.Conv2d(embed_dim // 4, embed_dim, 3, 1, 1)) + + ##################################################################################################### + ################################ 3, high quality image reconstruction ################################ + if self.upsampler == 'pixelshuffle': + # for classical SR + self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1), + nn.LeakyReLU(inplace=True)) + self.upsample = Upsample(upscale, num_feat) + self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) + elif self.upsampler == 'pixelshuffle_aux': + self.conv_bicubic = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1) + self.conv_before_upsample = nn.Sequential( + nn.Conv2d(embed_dim, num_feat, 3, 1, 1), + nn.LeakyReLU(inplace=True)) + self.conv_aux = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) + self.conv_after_aux = nn.Sequential( + nn.Conv2d(3, num_feat, 3, 1, 1), + nn.LeakyReLU(inplace=True)) + self.upsample = Upsample(upscale, num_feat) + self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) + + elif self.upsampler == 'pixelshuffle_hf': + self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1), + nn.LeakyReLU(inplace=True)) + self.upsample = Upsample(upscale, num_feat) + self.upsample_hf = Upsample_hf(upscale, num_feat) + self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) + self.conv_first_hf = nn.Sequential(nn.Conv2d(num_feat, embed_dim, 3, 1, 1), + nn.LeakyReLU(inplace=True)) + self.conv_after_body_hf = nn.Conv2d(embed_dim, embed_dim, 3, 1, 1) + self.conv_before_upsample_hf = nn.Sequential( + nn.Conv2d(embed_dim, num_feat, 3, 1, 1), + nn.LeakyReLU(inplace=True)) + self.conv_last_hf = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) + + elif self.upsampler == 'pixelshuffledirect': + # for lightweight SR (to save parameters) + self.upsample = UpsampleOneStep(upscale, embed_dim, num_out_ch, + (patches_resolution[0], patches_resolution[1])) + elif self.upsampler == 'nearest+conv': + # for real-world SR (less artifacts) + assert self.upscale == 4, 'only support x4 now.' + self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1), + nn.LeakyReLU(inplace=True)) + self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1) + self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1) + self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1) + self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) + self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True) + else: + # for image denoising and JPEG compression artifact reduction + self.conv_last = nn.Conv2d(embed_dim, num_out_ch, 3, 1, 1) + + self.apply(self._init_weights) + + def _init_weights(self, m): + if isinstance(m, nn.Linear): + trunc_normal_(m.weight, std=.02) + if isinstance(m, nn.Linear) and m.bias is not None: + nn.init.constant_(m.bias, 0) + elif isinstance(m, nn.LayerNorm): + nn.init.constant_(m.bias, 0) + nn.init.constant_(m.weight, 1.0) + + @torch.jit.ignore + def no_weight_decay(self): + return {'absolute_pos_embed'} + + @torch.jit.ignore + def no_weight_decay_keywords(self): + return {'relative_position_bias_table'} + + def check_image_size(self, x): + _, _, h, w = x.size() + mod_pad_h = (self.window_size - h % self.window_size) % self.window_size + mod_pad_w = (self.window_size - w % self.window_size) % self.window_size + x = F.pad(x, (0, mod_pad_w, 0, mod_pad_h), 'reflect') + return x + + def forward_features(self, x): + x_size = (x.shape[2], x.shape[3]) + x = self.patch_embed(x) + if self.ape: + x = x + self.absolute_pos_embed + x = self.pos_drop(x) + + for layer in self.layers: + x = layer(x, x_size) + + x = self.norm(x) # B L C + x = self.patch_unembed(x, x_size) + + return x + + def forward_features_hf(self, x): + x_size = (x.shape[2], x.shape[3]) + x = self.patch_embed(x) + if self.ape: + x = x + self.absolute_pos_embed + x = self.pos_drop(x) + + for layer in self.layers_hf: + x = layer(x, x_size) + + x = self.norm(x) # B L C + x = self.patch_unembed(x, x_size) + + return x + + def forward(self, x): + H, W = x.shape[2:] + x = self.check_image_size(x) + + self.mean = self.mean.type_as(x) + x = (x - self.mean) * self.img_range + + if self.upsampler == 'pixelshuffle': + # for classical SR + x = self.conv_first(x) + x = self.conv_after_body(self.forward_features(x)) + x + x = self.conv_before_upsample(x) + x = self.conv_last(self.upsample(x)) + elif self.upsampler == 'pixelshuffle_aux': + bicubic = F.interpolate(x, size=(H * self.upscale, W * self.upscale), mode='bicubic', align_corners=False) + bicubic = self.conv_bicubic(bicubic) + x = self.conv_first(x) + x = self.conv_after_body(self.forward_features(x)) + x + x = self.conv_before_upsample(x) + aux = self.conv_aux(x) # b, 3, LR_H, LR_W + x = self.conv_after_aux(aux) + x = self.upsample(x)[:, :, :H * self.upscale, :W * self.upscale] + bicubic[:, :, :H * self.upscale, :W * self.upscale] + x = self.conv_last(x) + aux = aux / self.img_range + self.mean + elif self.upsampler == 'pixelshuffle_hf': + # for classical SR with HF + x = self.conv_first(x) + x = self.conv_after_body(self.forward_features(x)) + x + x_before = self.conv_before_upsample(x) + x_out = self.conv_last(self.upsample(x_before)) + + x_hf = self.conv_first_hf(x_before) + x_hf = self.conv_after_body_hf(self.forward_features_hf(x_hf)) + x_hf + x_hf = self.conv_before_upsample_hf(x_hf) + x_hf = self.conv_last_hf(self.upsample_hf(x_hf)) + x = x_out + x_hf + x_hf = x_hf / self.img_range + self.mean + + elif self.upsampler == 'pixelshuffledirect': + # for lightweight SR + x = self.conv_first(x) + x = self.conv_after_body(self.forward_features(x)) + x + x = self.upsample(x) + elif self.upsampler == 'nearest+conv': + # for real-world SR + x = self.conv_first(x) + x = self.conv_after_body(self.forward_features(x)) + x + x = self.conv_before_upsample(x) + x = self.lrelu(self.conv_up1(torch.nn.functional.interpolate(x, scale_factor=2, mode='nearest'))) + x = self.lrelu(self.conv_up2(torch.nn.functional.interpolate(x, scale_factor=2, mode='nearest'))) + x = self.conv_last(self.lrelu(self.conv_hr(x))) + else: + # for image denoising and JPEG compression artifact reduction + x_first = self.conv_first(x) + res = self.conv_after_body(self.forward_features(x_first)) + x_first + x = x + self.conv_last(res) + + x = x / self.img_range + self.mean + if self.upsampler == "pixelshuffle_aux": + return x[:, :, :H*self.upscale, :W*self.upscale], aux + + elif self.upsampler == "pixelshuffle_hf": + x_out = x_out / self.img_range + self.mean + return x_out[:, :, :H*self.upscale, :W*self.upscale], x[:, :, :H*self.upscale, :W*self.upscale], x_hf[:, :, :H*self.upscale, :W*self.upscale] + + else: + return x[:, :, :H*self.upscale, :W*self.upscale] + + def flops(self): + flops = 0 + H, W = self.patches_resolution + flops += H * W * 3 * self.embed_dim * 9 + flops += self.patch_embed.flops() + for i, layer in enumerate(self.layers): + flops += layer.flops() + flops += H * W * 3 * self.embed_dim * self.embed_dim + flops += self.upsample.flops() + return flops + + +if __name__ == '__main__': + upscale = 4 + window_size = 8 + height = (1024 // upscale // window_size + 1) * window_size + width = (720 // upscale // window_size + 1) * window_size + model = Swin2SR(upscale=2, img_size=(height, width), + window_size=window_size, img_range=1., depths=[6, 6, 6, 6], + embed_dim=60, num_heads=[6, 6, 6, 6], mlp_ratio=2, upsampler='pixelshuffledirect') + print(model) + print(height, width, model.flops() / 1e9) + + x = torch.randn((1, 3, height, width)) + x = model(x) + print(x.shape) \ No newline at end of file From ed769977f0d0f201d8e361d365102f18775fc62c Mon Sep 17 00:00:00 2001 From: C43H66N12O12S2 <36072735+C43H66N12O12S2@users.noreply.github.com> Date: Sun, 9 Oct 2022 18:56:59 +0300 Subject: [PATCH 15/50] add swinir v2 support --- modules/swinir_model.py | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/modules/swinir_model.py b/modules/swinir_model.py index fbd11f8..baa02e3 100644 --- a/modules/swinir_model.py +++ b/modules/swinir_model.py @@ -10,6 +10,7 @@ from tqdm import tqdm from modules import modelloader from modules.shared import cmd_opts, opts, device from modules.swinir_model_arch import SwinIR as net +from modules.swinir_model_arch_v2 import Swin2SR as net2 from modules.upscaler import Upscaler, UpscalerData precision_scope = ( @@ -57,22 +58,42 @@ class UpscalerSwinIR(Upscaler): filename = path if filename is None or not os.path.exists(filename): return None - model = net( + if filename.endswith(".v2.pth"): + model = net2( upscale=scale, in_chans=3, img_size=64, window_size=8, img_range=1.0, - depths=[6, 6, 6, 6, 6, 6, 6, 6, 6], - embed_dim=240, - num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8], + depths=[6, 6, 6, 6, 6, 6], + embed_dim=180, + num_heads=[6, 6, 6, 6, 6, 6], mlp_ratio=2, upsampler="nearest+conv", - resi_connection="3conv", - ) + resi_connection="1conv", + ) + params = None + else: + model = net( + upscale=scale, + in_chans=3, + img_size=64, + window_size=8, + img_range=1.0, + depths=[6, 6, 6, 6, 6, 6, 6, 6, 6], + embed_dim=240, + num_heads=[8, 8, 8, 8, 8, 8, 8, 8, 8], + mlp_ratio=2, + upsampler="nearest+conv", + resi_connection="3conv", + ) + params = "params_ema" pretrained_model = torch.load(filename) - model.load_state_dict(pretrained_model["params_ema"], strict=True) + if params is not None: + model.load_state_dict(pretrained_model[params], strict=True) + else: + model.load_state_dict(pretrained_model, strict=True) if not cmd_opts.no_half: model = model.half() return model From af62ad4d25dcd0454944368f4925d83101cdedbc Mon Sep 17 00:00:00 2001 From: ssysm Date: Mon, 10 Oct 2022 13:25:28 -0400 Subject: [PATCH 16/50] change vae loading method --- modules/sd_models.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/modules/sd_models.py b/modules/sd_models.py index b0e1d8b..7a42d92 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -150,9 +150,16 @@ def load_model_weights(model, checkpoint_info): devices.dtype = torch.float32 if shared.cmd_opts.no_half else torch.float16 - vae_file = shared.cmd_opts.vae_path or os.path.splitext(checkpoint_file)[0] + ".vae.pt" + vae_file = os.path.splitext(checkpoint_file)[0] + ".vae.pt" + if os.path.exists(vae_file): + print(f"Found VAE Weights: {vae_file}") + elif shared.cmd_opts.vae_path != None: + vae_file = shared.cmd_opts.vae_path + print(f'No VAE found for inside the model folder. Using CLI specified : {vae_file}') + else: + print("No VAE found for inside the model folder. Passing.") + if os.path.exists(vae_file): - print(f"Loading VAE weights from: {vae_file}") vae_ckpt = torch.load(vae_file, map_location="cpu") vae_dict = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss"} From 39919c40dd18f5a14ae21403efea1b0f819756c7 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Mon, 10 Oct 2022 20:32:37 +0300 Subject: [PATCH 17/50] add eta noise seed delta option --- javascript/hints.js | 1 + modules/processing.py | 6 +++++- modules/shared.py | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/javascript/hints.js b/javascript/hints.js index 8e352e9..47b8077 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -79,6 +79,7 @@ titles = { "Highres. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition", "Scale latent": "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.", + "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.", } diff --git a/modules/processing.py b/modules/processing.py index 50ba4fc..698b306 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -207,7 +207,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see # enables the generation of additional tensors with noise that the sampler will use during its processing. # Using those pre-generated tensors instead of simple torch.randn allows a batch with seeds [100, 101] to # produce the same images as with two batches [100], [101]. - if p is not None and p.sampler is not None and len(seeds) > 1 and opts.enable_batch_seeds: + if p is not None and p.sampler is not None and (len(seeds) > 1 and opts.enable_batch_seeds or opts.eta_noise_seed_delta > 0): sampler_noises = [[] for _ in range(p.sampler.number_of_needed_noises(p))] else: sampler_noises = None @@ -247,6 +247,9 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see if sampler_noises is not None: cnt = p.sampler.number_of_needed_noises(p) + if opts.eta_noise_seed_delta > 0: + torch.manual_seed(seed + opts.eta_noise_seed_delta) + for j in range(cnt): sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape))) @@ -301,6 +304,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration "Denoising strength": getattr(p, 'denoising_strength', None), "Eta": (None if p.sampler is None or p.sampler.eta == p.sampler.default_eta else p.sampler.eta), "Clip skip": None if clip_skip <= 1 else clip_skip, + "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta, } generation_params.update(p.extra_generation_params) diff --git a/modules/shared.py b/modules/shared.py index 5dfc344..b1c65ec 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -260,6 +260,7 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters" 's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), 's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), + 'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}), })) From 727e4d108674dc2813507e2a973a733ef21e8d53 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Mon, 10 Oct 2022 20:46:55 +0300 Subject: [PATCH 18/50] no to different messages plus fix using != to compare to None --- modules/sd_models.py | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/modules/sd_models.py b/modules/sd_models.py index 4c06051..0a55b4c 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -152,15 +152,12 @@ def load_model_weights(model, checkpoint_info): devices.dtype_vae = torch.float32 if shared.cmd_opts.no_half or shared.cmd_opts.no_half_vae else torch.float16 vae_file = os.path.splitext(checkpoint_file)[0] + ".vae.pt" - if os.path.exists(vae_file): - print(f"Found VAE Weights: {vae_file}") - elif shared.cmd_opts.vae_path != None: + + if not os.path.exists(vae_file) and shared.cmd_opts.vae_path is not None: vae_file = shared.cmd_opts.vae_path - print(f'No VAE found for inside the model folder. Using CLI specified : {vae_file}') - else: - print("No VAE found for inside the model folder. Passing.") if os.path.exists(vae_file): + print(f"Loading VAE weights from: {vae_file}") vae_ckpt = torch.load(vae_file, map_location="cpu") vae_dict = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss"} From 5da1ba0e91a81804dc911d34c9a2e6956a23199c Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Mon, 10 Oct 2022 21:24:11 +0300 Subject: [PATCH 19/50] remove batch size restriction from X/Y plot --- scripts/xy_grid.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 771eb8e..42e1489 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -205,7 +205,10 @@ class Script(scripts.Script): if not no_fixed_seeds: modules.processing.fix_seed(p) - p.batch_size = 1 + if not opts.return_grid: + p.batch_size = 1 + + CLIP_stop_at_last_layers = opts.CLIP_stop_at_last_layers def process_axis(opt, vals): From f98338faa84ecce503e68d8ba13d5f7bbae52730 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Mon, 10 Oct 2022 23:15:48 +0300 Subject: [PATCH 20/50] add an option to not add watermark to created images --- javascript/hints.js | 1 + modules/shared.py | 1 + 2 files changed, 2 insertions(+) diff --git a/javascript/hints.js b/javascript/hints.js index 47b8077..045f2d3 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -80,6 +80,7 @@ titles = { "Scale latent": "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.", "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.", + "Do not add watermark to images": "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be bevaing in an unethical manner.", } diff --git a/modules/shared.py b/modules/shared.py index da389f9..ecd15ef 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -173,6 +173,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "use_original_name_batch": OptionInfo(False, "Use original name for output filename during batch process in extras tab"), "save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"), + "do_not_add_watermark": OptionInfo(False, "Do not add watermark to images"), })) options_templates.update(options_section(('saving-paths', "Paths for saving"), { From 42bf5fa3256bff5e4640e5a626e750d4e49e01e1 Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Mon, 10 Oct 2022 21:54:21 +0100 Subject: [PATCH 21/50] Make cancel generate forever let the current gen complete (#2206) --- javascript/contextMenus.js | 4 ---- 1 file changed, 4 deletions(-) diff --git a/javascript/contextMenus.js b/javascript/contextMenus.js index 2d82269..7852793 100644 --- a/javascript/contextMenus.js +++ b/javascript/contextMenus.js @@ -147,10 +147,6 @@ generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forev cancelGenerateForever = function(){ clearInterval(window.generateOnRepeatInterval) - let interruptbutton = gradioApp().querySelector('#txt2img_interrupt'); - if(interruptbutton.offsetParent){ - interruptbutton.click(); - } } appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever) From 70b50b1dfcb0ce0f87998c994f4855014bc7e26b Mon Sep 17 00:00:00 2001 From: ClashSAN <98228077+ClashSAN@users.noreply.github.com> Date: Mon, 10 Oct 2022 23:23:12 +0000 Subject: [PATCH 22/50] add features, credit for Composable Diffusion to readme https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2171 --- README.md | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 561eb03..0e93876 100644 --- a/README.md +++ b/README.md @@ -28,10 +28,12 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web - CodeFormer, face restoration tool as an alternative to GFPGAN - RealESRGAN, neural network upscaler - ESRGAN, neural network upscaler with a lot of third party models - - SwinIR, neural network upscaler + - SwinIR and Swin2SR([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers - LDSR, Latent diffusion super resolution upscaling - Resizing aspect ratio options - Sampling method selection + - Adjust sampler eta values (noise multiplier) + - More advanced noise setting options - Interrupt processing at any time - 4GB video card support (also reports of 2GB working) - Correct seeds for batches @@ -67,6 +69,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web - also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2` - No token limit for prompts (original stable diffusion lets you use up to 75 tokens) - DeepDanbooru integration, creates danbooru style tags for anime prompts (add --deepdanbooru to commandline args) +- [xformers](https://github.com/mv-lab/swin2sr), major speed increase for select cards: (add --xformers to commandline args) ## Installation and Running Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs. @@ -116,6 +119,7 @@ The documentation was moved from this README over to the project's [wiki](https: - CodeFormer - https://github.com/sczhou/CodeFormer - ESRGAN - https://github.com/xinntao/ESRGAN - SwinIR - https://github.com/JingyunLiang/SwinIR +- Swin2SR - https://github.com/mv-lab/swin2sr - LDSR - https://github.com/Hafiidz/latent-diffusion - Ideas for optimizations - https://github.com/basujindal/stable-diffusion - Doggettx - Cross Attention layer optimization - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing. @@ -123,6 +127,8 @@ The documentation was moved from this README over to the project's [wiki](https: - Idea for SD upscale - https://github.com/jquesnelle/txt2imghd - Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot - CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator +- Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch +- xformers - https://github.com/facebookresearch/xformers +- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user. -- DeepDanbooru - interrogator for anime diffusors https://github.com/KichangKim/DeepDanbooru - (You) From 8b7d3f1bef47bbe048f644ed0d8dd3ad46554045 Mon Sep 17 00:00:00 2001 From: Jairo Correa Date: Tue, 11 Oct 2022 02:22:46 -0300 Subject: [PATCH 23/50] Make the ctrl+enter shortcut use the generate button on the current tab --- modules/ui.py | 2 +- script.js | 11 +++++++++-- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/modules/ui.py b/modules/ui.py index e8039d7..cafda88 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1331,7 +1331,7 @@ Requested path was: {f} with gr.Tabs() as tabs: for interface, label, ifid in interfaces: - with gr.TabItem(label, id=ifid): + with gr.TabItem(label, id=ifid, elem_id='tab_' + ifid): interface.render() if os.path.exists(os.path.join(script_path, "notification.mp3")): diff --git a/script.js b/script.js index a92c0f7..9543cbe 100644 --- a/script.js +++ b/script.js @@ -6,6 +6,10 @@ function get_uiCurrentTab() { return gradioApp().querySelector('.tabs button:not(.border-transparent)') } +function get_uiCurrentTabContent() { + return gradioApp().querySelector('.tabitem[id^=tab_]:not([style*="display: none"])') +} + uiUpdateCallbacks = [] uiTabChangeCallbacks = [] let uiCurrentTab = null @@ -50,8 +54,11 @@ document.addEventListener("DOMContentLoaded", function() { } else if (e.keyCode !== undefined) { if((e.keyCode == 13 && (e.metaKey || e.ctrlKey))) handled = true; } - if (handled) { - gradioApp().querySelector("#txt2img_generate").click(); + if (handled) { + button = get_uiCurrentTabContent().querySelector('button[id$=_generate]'); + if (button) { + button.click(); + } e.preventDefault(); } }) From 8617396c6df71074c7fd3d39419802026874712a Mon Sep 17 00:00:00 2001 From: Kenneth Date: Mon, 10 Oct 2022 17:23:07 -0600 Subject: [PATCH 24/50] Added slider for deepbooru score threshold in settings --- modules/shared.py | 1 + modules/ui.py | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/modules/shared.py b/modules/shared.py index ecd15ef..e0830e2 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -239,6 +239,7 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"), "interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}), "interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}), "interrogate_clip_dict_limit": OptionInfo(1500, "Interrogate: maximum number of lines in text file (0 = No limit)"), + "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}), })) options_templates.update(options_section(('ui', "User interface"), { diff --git a/modules/ui.py b/modules/ui.py index cafda88..ca3151c 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -311,7 +311,7 @@ def interrogate(image): def interrogate_deepbooru(image): - prompt = get_deepbooru_tags(image) + prompt = get_deepbooru_tags(image, opts.interrogate_deepbooru_score_threshold) return gr_show(True) if prompt is None else prompt From 5e2627a1a63e4c9f87e6e604ecc24e9936f149de Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Tue, 11 Oct 2022 07:55:28 +0100 Subject: [PATCH 25/50] Comma backtrack padding (#2192) Comma backtrack padding --- modules/sd_hijack.py | 19 ++++++++++++++++++- modules/shared.py | 1 + 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 827bf30..aa4d2cb 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -107,6 +107,8 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): self.tokenizer = wrapped.tokenizer self.token_mults = {} + self.comma_token = [v for k, v in self.tokenizer.get_vocab().items() if k == ','][0] + tokens_with_parens = [(k, v) for k, v in self.tokenizer.get_vocab().items() if '(' in k or ')' in k or '[' in k or ']' in k] for text, ident in tokens_with_parens: mult = 1.0 @@ -136,6 +138,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): fixes = [] remade_tokens = [] multipliers = [] + last_comma = -1 for tokens, (text, weight) in zip(tokenized, parsed): i = 0 @@ -144,6 +147,20 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): embedding, embedding_length_in_tokens = self.hijack.embedding_db.find_embedding_at_position(tokens, i) + if token == self.comma_token: + last_comma = len(remade_tokens) + elif opts.comma_padding_backtrack != 0 and max(len(remade_tokens), 1) % 75 == 0 and last_comma != -1 and len(remade_tokens) - last_comma <= opts.comma_padding_backtrack: + last_comma += 1 + reloc_tokens = remade_tokens[last_comma:] + reloc_mults = multipliers[last_comma:] + + remade_tokens = remade_tokens[:last_comma] + length = len(remade_tokens) + + rem = int(math.ceil(length / 75)) * 75 - length + remade_tokens += [id_end] * rem + reloc_tokens + multipliers = multipliers[:last_comma] + [1.0] * rem + reloc_mults + if embedding is None: remade_tokens.append(token) multipliers.append(weight) @@ -284,7 +301,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): while max(map(len, remade_batch_tokens)) != 0: rem_tokens = [x[75:] for x in remade_batch_tokens] rem_multipliers = [x[75:] for x in batch_multipliers] - + self.hijack.fixes = [] for unfiltered in hijack_fixes: fixes = [] diff --git a/modules/shared.py b/modules/shared.py index e0830e2..14b40d7 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -227,6 +227,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"), "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."), "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"), + "comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }), "filter_nsfw": OptionInfo(False, "Filter NSFW content"), 'CLIP_stop_at_last_layers': OptionInfo(1, "Stop At last layers of CLIP model", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}), "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}), From 948533950c9db5069a874d925fadd50bac00fdb5 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 11:09:51 +0300 Subject: [PATCH 26/50] replace duplicate code with a function --- modules/hypernetwork.py | 23 ++++++++++------ modules/sd_hijack_optimizations.py | 44 ++++++++++-------------------- 2 files changed, 29 insertions(+), 38 deletions(-) diff --git a/modules/hypernetwork.py b/modules/hypernetwork.py index 498bc9d..7bbc443 100644 --- a/modules/hypernetwork.py +++ b/modules/hypernetwork.py @@ -64,21 +64,26 @@ def load_hypernetwork(filename): shared.loaded_hypernetwork = None +def apply_hypernetwork(hypernetwork, context): + hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) + + if hypernetwork_layers is None: + return context, context + + context_k = hypernetwork_layers[0](context) + context_v = hypernetwork_layers[1](context) + return context_k, context_v + + def attention_CrossAttention_forward(self, x, context=None, mask=None): h = self.heads q = self.to_q(x) context = default(context, x) - hypernetwork = shared.loaded_hypernetwork - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is not None: - k = self.to_k(hypernetwork_layers[0](context)) - v = self.to_v(hypernetwork_layers[1](context)) - else: - k = self.to_k(context) - v = self.to_v(context) + context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context) + k = self.to_k(context_k) + v = self.to_v(context_v) q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 18408e6..25cb67a 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -8,7 +8,8 @@ from torch import einsum from ldm.util import default from einops import rearrange -from modules import shared +from modules import shared, hypernetwork + if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers: try: @@ -26,16 +27,10 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None): q_in = self.to_q(x) context = default(context, x) - hypernetwork = shared.loaded_hypernetwork - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is not None: - k_in = self.to_k(hypernetwork_layers[0](context)) - v_in = self.to_v(hypernetwork_layers[1](context)) - else: - k_in = self.to_k(context) - v_in = self.to_v(context) - del context, x + context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context) + k_in = self.to_k(context_k) + v_in = self.to_v(context_v) + del context, context_k, context_v, x q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in)) del q_in, k_in, v_in @@ -59,22 +54,16 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None): return self.to_out(r2) -# taken from https://github.com/Doggettx/stable-diffusion +# taken from https://github.com/Doggettx/stable-diffusion and modified def split_cross_attention_forward(self, x, context=None, mask=None): h = self.heads q_in = self.to_q(x) context = default(context, x) - hypernetwork = shared.loaded_hypernetwork - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is not None: - k_in = self.to_k(hypernetwork_layers[0](context)) - v_in = self.to_v(hypernetwork_layers[1](context)) - else: - k_in = self.to_k(context) - v_in = self.to_v(context) + context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context) + k_in = self.to_k(context_k) + v_in = self.to_v(context_v) k_in *= self.scale @@ -130,14 +119,11 @@ def xformers_attention_forward(self, x, context=None, mask=None): h = self.heads q_in = self.to_q(x) context = default(context, x) - hypernetwork = shared.loaded_hypernetwork - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - if hypernetwork_layers is not None: - k_in = self.to_k(hypernetwork_layers[0](context)) - v_in = self.to_v(hypernetwork_layers[1](context)) - else: - k_in = self.to_k(context) - v_in = self.to_v(context) + + context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context) + k_in = self.to_k(context_k) + v_in = self.to_v(context_v) + q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b n h d', h=h), (q_in, k_in, v_in)) del q_in, k_in, v_in out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None) From 255be75d30f41e089e499ec1c8462d6bf64dec24 Mon Sep 17 00:00:00 2001 From: aperullo <18688190+aperullo@users.noreply.github.com> Date: Tue, 11 Oct 2022 06:16:57 -0400 Subject: [PATCH 27/50] Error if prompt missing SR token to prevent mis-gens (#2209) --- scripts/xy_grid.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 42e1489..10a82dc 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -27,9 +27,16 @@ def apply_field(field): def apply_prompt(p, x, xs): + + orig_prompt = p.prompt + orig_negative_prompt = p.negative_prompt + p.prompt = p.prompt.replace(xs[0], x) p.negative_prompt = p.negative_prompt.replace(xs[0], x) + if p.prompt == orig_prompt and p.negative_prompt == orig_negative_prompt: + raise RuntimeError(f"Prompt S/R did not find {xs[0]} in prompt or negative prompt. Did you forget to add the token?") + def apply_order(p, x, xs): token_order = [] From 4b460fcb1a0224772949556fe0469da93245c532 Mon Sep 17 00:00:00 2001 From: Rory Grieve Date: Tue, 11 Oct 2022 11:23:47 +0100 Subject: [PATCH 28/50] Reset init img in loopback at start of each batch (#2214) Before a new batch would use the last image from the previous batch. Now each batch will use the original image for the init image at the start of the batch. --- scripts/loopback.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/scripts/loopback.py b/scripts/loopback.py index e90b58d..d8c68af 100644 --- a/scripts/loopback.py +++ b/scripts/loopback.py @@ -38,6 +38,7 @@ class Script(scripts.Script): grids = [] all_images = [] + original_init_image = p.init_images state.job_count = loops * batch_count initial_color_corrections = [processing.setup_color_correction(p.init_images[0])] @@ -45,6 +46,9 @@ class Script(scripts.Script): for n in range(batch_count): history = [] + # Reset to original init image at the start of each batch + p.init_images = original_init_image + for i in range(loops): p.n_iter = 1 p.batch_size = 1 From a8490e4019c359ff24824e004059744d7164361b Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Tue, 11 Oct 2022 11:42:41 +0100 Subject: [PATCH 29/50] revert sr warning --- scripts/xy_grid.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 10a82dc..99b3c4f 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -35,7 +35,8 @@ def apply_prompt(p, x, xs): p.negative_prompt = p.negative_prompt.replace(xs[0], x) if p.prompt == orig_prompt and p.negative_prompt == orig_negative_prompt: - raise RuntimeError(f"Prompt S/R did not find {xs[0]} in prompt or negative prompt. Did you forget to add the token?") + pass + #raise RuntimeError(f"Prompt S/R did not find {xs[0]} in prompt or negative prompt. Did you forget to add the token?") def apply_order(p, x, xs): From 1a0a6a84c3149e236211d547471f5416cd1129f3 Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Tue, 11 Oct 2022 11:59:56 +0100 Subject: [PATCH 30/50] add incorrect start word guard to xy_grid (#2259) --- scripts/xy_grid.py | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 99b3c4f..9d4d618 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -27,17 +27,12 @@ def apply_field(field): def apply_prompt(p, x, xs): - - orig_prompt = p.prompt - orig_negative_prompt = p.negative_prompt + if xs[0] not in p.prompt and xs[0] not in p.negative_prompt: + raise RuntimeError(f"Prompt S/R did not find {xs[0]} in prompt or negative prompt.") p.prompt = p.prompt.replace(xs[0], x) p.negative_prompt = p.negative_prompt.replace(xs[0], x) - if p.prompt == orig_prompt and p.negative_prompt == orig_negative_prompt: - pass - #raise RuntimeError(f"Prompt S/R did not find {xs[0]} in prompt or negative prompt. Did you forget to add the token?") - def apply_order(p, x, xs): token_order = [] From 530103b586109c11fd068eb70ef09503ec6a4caf Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 14:53:02 +0300 Subject: [PATCH 31/50] fixes related to merge --- modules/hypernetwork.py | 103 ------------------ modules/hypernetwork/hypernetwork.py | 82 ++++++++------ modules/hypernetwork/ui.py | 10 +- modules/sd_hijack_optimizations.py | 3 +- modules/shared.py | 13 ++- .../textual_inversion/textual_inversion.py | 12 +- modules/ui.py | 5 +- scripts/xy_grid.py | 3 +- webui.py | 15 +-- 9 files changed, 82 insertions(+), 164 deletions(-) delete mode 100644 modules/hypernetwork.py diff --git a/modules/hypernetwork.py b/modules/hypernetwork.py deleted file mode 100644 index 7bbc443..0000000 --- a/modules/hypernetwork.py +++ /dev/null @@ -1,103 +0,0 @@ -import glob -import os -import sys -import traceback - -import torch - -from ldm.util import default -from modules import devices, shared -import torch -from torch import einsum -from einops import rearrange, repeat - - -class HypernetworkModule(torch.nn.Module): - def __init__(self, dim, state_dict): - super().__init__() - - self.linear1 = torch.nn.Linear(dim, dim * 2) - self.linear2 = torch.nn.Linear(dim * 2, dim) - - self.load_state_dict(state_dict, strict=True) - self.to(devices.device) - - def forward(self, x): - return x + (self.linear2(self.linear1(x))) - - -class Hypernetwork: - filename = None - name = None - - def __init__(self, filename): - self.filename = filename - self.name = os.path.splitext(os.path.basename(filename))[0] - self.layers = {} - - state_dict = torch.load(filename, map_location='cpu') - for size, sd in state_dict.items(): - self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1])) - - -def list_hypernetworks(path): - res = {} - for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True): - name = os.path.splitext(os.path.basename(filename))[0] - res[name] = filename - return res - - -def load_hypernetwork(filename): - path = shared.hypernetworks.get(filename, None) - if path is not None: - print(f"Loading hypernetwork {filename}") - try: - shared.loaded_hypernetwork = Hypernetwork(path) - except Exception: - print(f"Error loading hypernetwork {path}", file=sys.stderr) - print(traceback.format_exc(), file=sys.stderr) - else: - if shared.loaded_hypernetwork is not None: - print(f"Unloading hypernetwork") - - shared.loaded_hypernetwork = None - - -def apply_hypernetwork(hypernetwork, context): - hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is None: - return context, context - - context_k = hypernetwork_layers[0](context) - context_v = hypernetwork_layers[1](context) - return context_k, context_v - - -def attention_CrossAttention_forward(self, x, context=None, mask=None): - h = self.heads - - q = self.to_q(x) - context = default(context, x) - - context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context) - k = self.to_k(context_k) - v = self.to_v(context_v) - - q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v)) - - sim = einsum('b i d, b j d -> b i j', q, k) * self.scale - - if mask is not None: - mask = rearrange(mask, 'b ... -> b (...)') - max_neg_value = -torch.finfo(sim.dtype).max - mask = repeat(mask, 'b j -> (b h) () j', h=h) - sim.masked_fill_(~mask, max_neg_value) - - # attention, what we cannot get enough of - attn = sim.softmax(dim=-1) - - out = einsum('b i j, b j d -> b i d', attn, v) - out = rearrange(out, '(b h) n d -> b n (h d)', h=h) - return self.to_out(out) diff --git a/modules/hypernetwork/hypernetwork.py b/modules/hypernetwork/hypernetwork.py index a3d6a47..aa701bd 100644 --- a/modules/hypernetwork/hypernetwork.py +++ b/modules/hypernetwork/hypernetwork.py @@ -26,10 +26,11 @@ class HypernetworkModule(torch.nn.Module): if state_dict is not None: self.load_state_dict(state_dict, strict=True) else: - self.linear1.weight.data.fill_(0.0001) - self.linear1.bias.data.fill_(0.0001) - self.linear2.weight.data.fill_(0.0001) - self.linear2.bias.data.fill_(0.0001) + + self.linear1.weight.data.normal_(mean=0.0, std=0.01) + self.linear1.bias.data.zero_() + self.linear2.weight.data.normal_(mean=0.0, std=0.01) + self.linear2.bias.data.zero_() self.to(devices.device) @@ -92,41 +93,54 @@ class Hypernetwork: self.sd_checkpoint_name = state_dict.get('sd_checkpoint_name', None) -def load_hypernetworks(path): +def list_hypernetworks(path): res = {} - - for filename in glob.iglob(path + '**/*.pt', recursive=True): - try: - hn = Hypernetwork() - hn.load(filename) - res[hn.name] = hn - except Exception: - print(f"Error loading hypernetwork {filename}", file=sys.stderr) - print(traceback.format_exc(), file=sys.stderr) - + for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True): + name = os.path.splitext(os.path.basename(filename))[0] + res[name] = filename return res +def load_hypernetwork(filename): + path = shared.hypernetworks.get(filename, None) + if path is not None: + print(f"Loading hypernetwork {filename}") + try: + shared.loaded_hypernetwork = Hypernetwork() + shared.loaded_hypernetwork.load(path) + + except Exception: + print(f"Error loading hypernetwork {path}", file=sys.stderr) + print(traceback.format_exc(), file=sys.stderr) + else: + if shared.loaded_hypernetwork is not None: + print(f"Unloading hypernetwork") + + shared.loaded_hypernetwork = None + + +def apply_hypernetwork(hypernetwork, context, layer=None): + hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None) + + if hypernetwork_layers is None: + return context, context + + if layer is not None: + layer.hyper_k = hypernetwork_layers[0] + layer.hyper_v = hypernetwork_layers[1] + + context_k = hypernetwork_layers[0](context) + context_v = hypernetwork_layers[1](context) + return context_k, context_v + + def attention_CrossAttention_forward(self, x, context=None, mask=None): h = self.heads q = self.to_q(x) context = default(context, x) - hypernetwork_layers = (shared.hypernetwork.layers if shared.hypernetwork is not None else {}).get(context.shape[2], None) - - if hypernetwork_layers is not None: - hypernetwork_k, hypernetwork_v = hypernetwork_layers - - self.hypernetwork_k = hypernetwork_k - self.hypernetwork_v = hypernetwork_v - - context_k = hypernetwork_k(context) - context_v = hypernetwork_v(context) - else: - context_k = context - context_v = context - + context_k, context_v = apply_hypernetwork(shared.loaded_hypernetwork, context, self) k = self.to_k(context_k) v = self.to_v(context_v) @@ -151,7 +165,9 @@ def attention_CrossAttention_forward(self, x, context=None, mask=None): def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, steps, create_image_every, save_hypernetwork_every, template_file, preview_image_prompt): assert hypernetwork_name, 'embedding not selected' - shared.hypernetwork = shared.hypernetworks[hypernetwork_name] + path = shared.hypernetworks.get(hypernetwork_name, None) + shared.loaded_hypernetwork = Hypernetwork() + shared.loaded_hypernetwork.load(path) shared.state.textinfo = "Initializing hypernetwork training..." shared.state.job_count = steps @@ -176,9 +192,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..." with torch.autocast("cuda"): - ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, size=512, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file) + ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=512, height=512, repeats=1, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file) - hypernetwork = shared.hypernetworks[hypernetwork_name] + hypernetwork = shared.loaded_hypernetwork weights = hypernetwork.weights() for weight in weights: weight.requires_grad = True @@ -194,7 +210,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory, if ititial_step > steps: return hypernetwork, filename - pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step) + pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step) for i, (x, text) in pbar: hypernetwork.step = i + ititial_step diff --git a/modules/hypernetwork/ui.py b/modules/hypernetwork/ui.py index 525f978..f6d1d0a 100644 --- a/modules/hypernetwork/ui.py +++ b/modules/hypernetwork/ui.py @@ -6,24 +6,24 @@ import gradio as gr import modules.textual_inversion.textual_inversion import modules.textual_inversion.preprocess from modules import sd_hijack, shared +from modules.hypernetwork import hypernetwork def create_hypernetwork(name): fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") assert not os.path.exists(fn), f"file {fn} already exists" - hypernetwork = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) - hypernetwork.save(fn) + hypernet = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) + hypernet.save(fn) shared.reload_hypernetworks() - shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None) return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", "" def train_hypernetwork(*args): - initial_hypernetwork = shared.hypernetwork + initial_hypernetwork = shared.loaded_hypernetwork try: sd_hijack.undo_optimizations() @@ -38,6 +38,6 @@ Hypernetwork saved to {html.escape(filename)} except Exception: raise finally: - shared.hypernetwork = initial_hypernetwork + shared.loaded_hypernetwork = initial_hypernetwork sd_hijack.apply_optimizations() diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 25cb67a..27e571f 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -8,7 +8,8 @@ from torch import einsum from ldm.util import default from einops import rearrange -from modules import shared, hypernetwork +from modules import shared +from modules.hypernetwork import hypernetwork if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers: diff --git a/modules/shared.py b/modules/shared.py index 14b40d7..8753015 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -13,7 +13,8 @@ import modules.memmon import modules.sd_models import modules.styles import modules.devices as devices -from modules import sd_samplers, hypernetwork +from modules import sd_samplers +from modules.hypernetwork import hypernetwork from modules.paths import models_path, script_path, sd_path sd_model_file = os.path.join(script_path, 'model.ckpt') @@ -29,6 +30,7 @@ parser.add_argument("--no-half-vae", action='store_true', help="do not switch th parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)") parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI") parser.add_argument("--embeddings-dir", type=str, default=os.path.join(script_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)") +parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory") parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui") parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage") parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage") @@ -82,10 +84,17 @@ parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram xformers_available = False config_filename = cmd_opts.ui_settings_file -hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks')) +hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir) loaded_hypernetwork = None +def reload_hypernetworks(): + global hypernetworks + + hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir) + hypernetwork.load_hypernetwork(opts.sd_hypernetwork) + + class State: skipped = False interrupted = False diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 5965c5a..d697795 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -156,7 +156,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'): return fn -def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file): +def train_embedding(embedding_name, learn_rate, data_root, log_directory, training_width, training_height, steps, num_repeats, create_image_every, save_embedding_every, template_file, preview_image_prompt): assert embedding_name, 'embedding not selected' shared.state.textinfo = "Initializing textual inversion training..." @@ -238,12 +238,14 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini if embedding.step > 0 and images_dir is not None and embedding.step % create_image_every == 0: last_saved_image = os.path.join(images_dir, f'{embedding_name}-{embedding.step}.png') + preview_text = text if preview_image_prompt == "" else preview_image_prompt + p = processing.StableDiffusionProcessingTxt2Img( sd_model=shared.sd_model, - prompt=text, + prompt=preview_text, steps=20, - height=training_height, - width=training_width, + height=training_height, + width=training_width, do_not_save_grid=True, do_not_save_samples=True, ) @@ -254,7 +256,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini shared.state.current_image = image image.save(last_saved_image) - last_saved_image += f", prompt: {text}" + last_saved_image += f", prompt: {preview_text}" shared.state.job_no = embedding.step diff --git a/modules/ui.py b/modules/ui.py index 10b1ee3..df65305 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1023,7 +1023,7 @@ def create_ui(wrap_gradio_gpu_call): gr.HTML(value="") with gr.Column(): - create_embedding = gr.Button(value="Create", variant='primary') + create_embedding = gr.Button(value="Create embedding", variant='primary') with gr.Group(): gr.HTML(value="

Create a new hypernetwork

") @@ -1035,7 +1035,7 @@ def create_ui(wrap_gradio_gpu_call): gr.HTML(value="") with gr.Column(): - create_hypernetwork = gr.Button(value="Create", variant='primary') + create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary') with gr.Group(): gr.HTML(value="

Preprocess images

") @@ -1147,6 +1147,7 @@ def create_ui(wrap_gradio_gpu_call): create_image_every, save_embedding_every, template_file, + preview_image_prompt, ], outputs=[ ti_output, diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 42e1489..0af5993 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -10,7 +10,8 @@ import numpy as np import modules.scripts as scripts import gradio as gr -from modules import images, hypernetwork +from modules import images +from modules.hypernetwork import hypernetwork from modules.processing import process_images, Processed, get_correct_sampler from modules.shared import opts, cmd_opts, state import modules.shared as shared diff --git a/webui.py b/webui.py index 7c20055..ba2156c 100644 --- a/webui.py +++ b/webui.py @@ -29,6 +29,7 @@ from modules import devices from modules import modelloader from modules.paths import script_path from modules.shared import cmd_opts +import modules.hypernetwork.hypernetwork modelloader.cleanup_models() modules.sd_models.setup_model() @@ -77,22 +78,12 @@ def wrap_gradio_gpu_call(func, extra_outputs=None): return modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs) -def set_hypernetwork(): - shared.hypernetwork = shared.hypernetworks.get(shared.opts.sd_hypernetwork, None) - - -shared.reload_hypernetworks() -shared.opts.onchange("sd_hypernetwork", set_hypernetwork) -set_hypernetwork() - - modules.scripts.load_scripts(os.path.join(script_path, "scripts")) shared.sd_model = modules.sd_models.load_model() shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model))) -loaded_hypernetwork = modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork) -shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork))) +shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork))) def webui(): @@ -117,7 +108,7 @@ def webui(): prevent_thread_lock=True ) - app.add_middleware(GZipMiddleware,minimum_size=1000) + app.add_middleware(GZipMiddleware, minimum_size=1000) while 1: time.sleep(0.5) From 45ada1c91025e221df04f911de6377e419f19e3f Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Tue, 11 Oct 2022 13:10:11 +0100 Subject: [PATCH 32/50] Correct list style, apply gen forever to both tabs, roll3 on both tabs --- javascript/contextMenus.js | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/javascript/contextMenus.js b/javascript/contextMenus.js index 7852793..4e77206 100644 --- a/javascript/contextMenus.js +++ b/javascript/contextMenus.js @@ -16,7 +16,7 @@ contextMenuInit = function(){ oldMenu.remove() } - let tabButton = gradioApp().querySelector('button') + let tabButton = uiCurrentTab let baseStyle = window.getComputedStyle(tabButton) const contextMenu = document.createElement('nav') @@ -130,9 +130,9 @@ addContextMenuEventListener = initResponse[2] //Start example Context Menu Items -generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forever',function(){ - let genbutton = gradioApp().querySelector('#txt2img_generate'); - let interruptbutton = gradioApp().querySelector('#txt2img_interrupt'); +generateOnRepeat = function(genbuttonid,interruptbuttonid){ + let genbutton = gradioApp().querySelector(genbuttonid); + let interruptbutton = gradioApp().querySelector(interruptbuttonid); if(!interruptbutton.offsetParent){ genbutton.click(); } @@ -142,8 +142,15 @@ generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forev genbutton.click(); } }, - 500)} -) + 500) +} + +generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forever',function(){ + generateOnRepeat('#txt2img_generate','#txt2img_interrupt'); +}) +generateOnRepeatId = appendContextMenuOption('#img2img_generate','Generate forever',function(){ + generateOnRepeat('#img2img_generate','#img2img_interrupt'); +}) cancelGenerateForever = function(){ clearInterval(window.generateOnRepeatInterval) @@ -151,11 +158,12 @@ cancelGenerateForever = function(){ appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever) appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever) - +appendContextMenuOption('#img2img_interrupt','Cancel generate forever',cancelGenerateForever) +appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever) appendContextMenuOption('#roll','Roll three', function(){ - let rollbutton = gradioApp().querySelector('#roll'); + let rollbutton = get_uiCurrentTabContent().querySelector('#roll'); setTimeout(function(){rollbutton.click()},100) setTimeout(function(){rollbutton.click()},200) setTimeout(function(){rollbutton.click()},300) From 9b8faefde05464fe6ba51668fe1d361e4fe22339 Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Tue, 11 Oct 2022 13:19:16 +0100 Subject: [PATCH 33/50] context menus closure --- javascript/contextMenus.js | 83 +++++++++++++++++++------------------- 1 file changed, 42 insertions(+), 41 deletions(-) diff --git a/javascript/contextMenus.js b/javascript/contextMenus.js index 4e77206..7636c4b 100644 --- a/javascript/contextMenus.js +++ b/javascript/contextMenus.js @@ -123,52 +123,53 @@ contextMenuInit = function(){ return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener] } -initResponse = contextMenuInit() -appendContextMenuOption = initResponse[0] -removeContextMenuOption = initResponse[1] -addContextMenuEventListener = initResponse[2] +initResponse = contextMenuInit(); +appendContextMenuOption = initResponse[0]; +removeContextMenuOption = initResponse[1]; +addContextMenuEventListener = initResponse[2]; - -//Start example Context Menu Items -generateOnRepeat = function(genbuttonid,interruptbuttonid){ - let genbutton = gradioApp().querySelector(genbuttonid); - let interruptbutton = gradioApp().querySelector(interruptbuttonid); - if(!interruptbutton.offsetParent){ - genbutton.click(); - } - clearInterval(window.generateOnRepeatInterval) - window.generateOnRepeatInterval = setInterval(function(){ +(function(){ + //Start example Context Menu Items + let generateOnRepeat = function(genbuttonid,interruptbuttonid){ + let genbutton = gradioApp().querySelector(genbuttonid); + let interruptbutton = gradioApp().querySelector(interruptbuttonid); if(!interruptbutton.offsetParent){ genbutton.click(); } - }, - 500) -} - -generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forever',function(){ - generateOnRepeat('#txt2img_generate','#txt2img_interrupt'); -}) -generateOnRepeatId = appendContextMenuOption('#img2img_generate','Generate forever',function(){ - generateOnRepeat('#img2img_generate','#img2img_interrupt'); -}) - -cancelGenerateForever = function(){ - clearInterval(window.generateOnRepeatInterval) -} - -appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever) -appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever) -appendContextMenuOption('#img2img_interrupt','Cancel generate forever',cancelGenerateForever) -appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever) - -appendContextMenuOption('#roll','Roll three', - function(){ - let rollbutton = get_uiCurrentTabContent().querySelector('#roll'); - setTimeout(function(){rollbutton.click()},100) - setTimeout(function(){rollbutton.click()},200) - setTimeout(function(){rollbutton.click()},300) + clearInterval(window.generateOnRepeatInterval) + window.generateOnRepeatInterval = setInterval(function(){ + if(!interruptbutton.offsetParent){ + genbutton.click(); + } + }, + 500) } -) + + appendContextMenuOption('#txt2img_generate','Generate forever',function(){ + generateOnRepeat('#txt2img_generate','#txt2img_interrupt'); + }) + appendContextMenuOption('#img2img_generate','Generate forever',function(){ + generateOnRepeat('#img2img_generate','#img2img_interrupt'); + }) + + let cancelGenerateForever = function(){ + clearInterval(window.generateOnRepeatInterval) + } + + appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever) + appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever) + appendContextMenuOption('#img2img_interrupt','Cancel generate forever',cancelGenerateForever) + appendContextMenuOption('#img2img_generate', 'Cancel generate forever',cancelGenerateForever) + + appendContextMenuOption('#roll','Roll three', + function(){ + let rollbutton = get_uiCurrentTabContent().querySelector('#roll'); + setTimeout(function(){rollbutton.click()},100) + setTimeout(function(){rollbutton.click()},200) + setTimeout(function(){rollbutton.click()},300) + } + ) +})(); //End example Context Menu Items onUiUpdate(function(){ From 92d7a138857b308c97a8d009848f642aeb93d6c8 Mon Sep 17 00:00:00 2001 From: Martin Cairns Date: Tue, 11 Oct 2022 00:02:44 +0100 Subject: [PATCH 34/50] Handle different parameters for DPM fast & adaptive --- modules/sd_samplers.py | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index d168b93..eee52e7 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -57,7 +57,7 @@ def set_samplers(): global samplers, samplers_for_img2img hidden = set(opts.hide_samplers) - hidden_img2img = set(opts.hide_samplers + ['PLMS', 'DPM fast', 'DPM adaptive']) + hidden_img2img = set(opts.hide_samplers + ['PLMS']) samplers = [x for x in all_samplers if x.name not in hidden] samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img] @@ -365,16 +365,27 @@ class KDiffusionSampler: else: sigmas = self.model_wrap.get_sigmas(steps) - noise = noise * sigmas[steps - t_enc - 1] - xi = x + noise - - extra_params_kwargs = self.initialize(p) - sigma_sched = sigmas[steps - t_enc - 1:] + print('check values same', sigmas[steps - t_enc - 1] , sigma_sched[0], sigmas[steps - t_enc - 1] - sigma_sched[0]) + xi = x + noise * sigma_sched[0] + + extra_params_kwargs = self.initialize(p) + if 'sigma_min' in inspect.signature(self.func).parameters: + ## last sigma is zero which is allowed by DPM Fast & Adaptive so taking value before last + extra_params_kwargs['sigma_min'] = sigma_sched[-2] + if 'sigma_max' in inspect.signature(self.func).parameters: + extra_params_kwargs['sigma_max'] = sigma_sched[0] + if 'n' in inspect.signature(self.func).parameters: + extra_params_kwargs['n'] = len(sigma_sched) - 1 + if 'sigma_sched' in inspect.signature(self.func).parameters: + extra_params_kwargs['sigma_sched'] = sigma_sched + if 'sigmas' in inspect.signature(self.func).parameters: + extra_params_kwargs['sigmas'] = sigma_sched self.model_wrap_cfg.init_latent = x - return self.func(self.model_wrap_cfg, xi, sigma_sched, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs) + return self.func(self.model_wrap_cfg, xi, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs) + def sample(self, p, x, conditioning, unconditional_conditioning, steps=None): steps = steps or p.steps From 1eae3076078f00ecc5d0fac3c77fffb85cd2eb77 Mon Sep 17 00:00:00 2001 From: Martin Cairns Date: Tue, 11 Oct 2022 00:04:06 +0100 Subject: [PATCH 35/50] Remove debug code for checking that first sigma value is same after code cleanup --- modules/sd_samplers.py | 1 - 1 file changed, 1 deletion(-) diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index eee52e7..3227291 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -366,7 +366,6 @@ class KDiffusionSampler: sigmas = self.model_wrap.get_sigmas(steps) sigma_sched = sigmas[steps - t_enc - 1:] - print('check values same', sigmas[steps - t_enc - 1] , sigma_sched[0], sigmas[steps - t_enc - 1] - sigma_sched[0]) xi = x + noise * sigma_sched[0] extra_params_kwargs = self.initialize(p) From eacc03b16730bcc5be95cda2d7c966ff1b4a8263 Mon Sep 17 00:00:00 2001 From: Martin Cairns Date: Tue, 11 Oct 2022 00:36:00 +0100 Subject: [PATCH 36/50] Fix typo in comments --- modules/sd_samplers.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 3227291..20309e0 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -370,7 +370,7 @@ class KDiffusionSampler: extra_params_kwargs = self.initialize(p) if 'sigma_min' in inspect.signature(self.func).parameters: - ## last sigma is zero which is allowed by DPM Fast & Adaptive so taking value before last + ## last sigma is zero which isn't allowed by DPM Fast & Adaptive so taking value before last extra_params_kwargs['sigma_min'] = sigma_sched[-2] if 'sigma_max' in inspect.signature(self.func).parameters: extra_params_kwargs['sigma_max'] = sigma_sched[0] From b372f5538bee4feba87080af4f3acf1e437accc6 Mon Sep 17 00:00:00 2001 From: Ben <110583491+TheLastBen@users.noreply.github.com> Date: Mon, 10 Oct 2022 19:34:07 +0100 Subject: [PATCH 37/50] Save some space --- style.css | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/style.css b/style.css index 00a3d07..38410ca 100644 --- a/style.css +++ b/style.css @@ -2,6 +2,18 @@ max-width: 100%; } +#txt2img_token_counter { + height: 0px; +} + +#img2img_token_counter { + height: 0px; +} + +#negative_prompt { + width: 97.9%; +} + .output-html p {margin: 0 0.5em;} .row > *, From 87b77cad5f3017c952a7dfec0e7904a9df5b72fd Mon Sep 17 00:00:00 2001 From: Ben <110583491+TheLastBen@users.noreply.github.com> Date: Mon, 10 Oct 2022 19:37:16 +0100 Subject: [PATCH 38/50] Layout fix --- modules/ui.py | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/modules/ui.py b/modules/ui.py index df65305..de4cd7f 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -550,15 +550,15 @@ def create_ui(wrap_gradio_gpu_call): button_id = "hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder' open_txt2img_folder = gr.Button(folder_symbol, elem_id=button_id) - with gr.Row(): - do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False) + with gr.Row(): + do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False) - with gr.Row(): - download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False) + with gr.Row(): + download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False) - with gr.Group(): - html_info = gr.HTML() - generation_info = gr.Textbox(visible=False) + with gr.Group(): + html_info = gr.HTML() + generation_info = gr.Textbox(visible=False) connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False) connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True) @@ -738,15 +738,15 @@ def create_ui(wrap_gradio_gpu_call): button_id = "hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder' open_img2img_folder = gr.Button(folder_symbol, elem_id=button_id) - with gr.Row(): - do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False) + with gr.Row(): + do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False) - with gr.Row(): - download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False) + with gr.Row(): + download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False) - with gr.Group(): - html_info = gr.HTML() - generation_info = gr.Textbox(visible=False) + with gr.Group(): + html_info = gr.HTML() + generation_info = gr.Textbox(visible=False) connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False) connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True) From 861297cefe2bb663f4e09dd4778a4cb93ebe8ff1 Mon Sep 17 00:00:00 2001 From: Ben <110583491+TheLastBen@users.noreply.github.com> Date: Tue, 11 Oct 2022 08:08:45 +0100 Subject: [PATCH 39/50] add a space holder --- modules/ui.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/modules/ui.py b/modules/ui.py index de4cd7f..fc0f3d3 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -429,7 +429,10 @@ def create_toprow(is_img2img): with gr.Row(): with gr.Column(scale=8): - negative_prompt = gr.Textbox(label="Negative prompt", elem_id="negative_prompt", show_label=False, placeholder="Negative prompt", lines=2) + with gr.Row(): + negative_prompt = gr.Textbox(label="Negative prompt", elem_id="negative_prompt", show_label=False, placeholder="Negative prompt", lines=2) + with gr.Column(scale=1, elem_id="roll_col"): + sh = gr.Button(elem_id="sh", visible=True) with gr.Column(scale=1, elem_id="style_neg_col"): prompt_style2 = gr.Dropdown(label="Style 2", elem_id=f"{id_part}_style2_index", choices=[k for k, v in shared.prompt_styles.styles.items()], value=next(iter(shared.prompt_styles.styles.keys())), visible=len(shared.prompt_styles.styles) > 1) From 031dc8cd7fa6bc74b44114715b28e0737342de37 Mon Sep 17 00:00:00 2001 From: Ben <110583491+TheLastBen@users.noreply.github.com> Date: Tue, 11 Oct 2022 08:08:47 +0100 Subject: [PATCH 40/50] space holder --- style.css | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/style.css b/style.css index 38410ca..d1c866f 100644 --- a/style.css +++ b/style.css @@ -10,8 +10,16 @@ height: 0px; } -#negative_prompt { - width: 97.9%; +#sh{ + min-width: 2em; + min-height: 2em; + max-width: 2em; + max-height: 2em; + flex-grow: 0; + padding-left: 0.25em; + padding-right: 0.25em; + margin: 0.1em 0; + opacity: 0%; } .output-html p {margin: 0 0.5em;} From 54c519943a24881ea61af5a73dedbab92f9431ce Mon Sep 17 00:00:00 2001 From: Ben <110583491+TheLastBen@users.noreply.github.com> Date: Tue, 11 Oct 2022 10:16:53 +0100 Subject: [PATCH 41/50] Update style.css --- style.css | 1 + 1 file changed, 1 insertion(+) diff --git a/style.css b/style.css index d1c866f..ecb51bb 100644 --- a/style.css +++ b/style.css @@ -20,6 +20,7 @@ padding-right: 0.25em; margin: 0.1em 0; opacity: 0%; + cursor: default; } .output-html p {margin: 0 0.5em;} From 210fd72babb8314b280a7b5ef8603c62024a22db Mon Sep 17 00:00:00 2001 From: parsec501 <105080989+parsec501@users.noreply.github.com> Date: Tue, 11 Oct 2022 14:37:01 +0200 Subject: [PATCH 42/50] Added 'suggestion' flair to suggestion template --- .github/ISSUE_TEMPLATE/feature_request.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md index bbcbbe7..eda42fa 100644 --- a/.github/ISSUE_TEMPLATE/feature_request.md +++ b/.github/ISSUE_TEMPLATE/feature_request.md @@ -2,7 +2,7 @@ name: Feature request about: Suggest an idea for this project title: '' -labels: '' +labels: 'suggestion' assignees: '' --- From 4e485b79238666ace2b270045f73a12e5ccc7af9 Mon Sep 17 00:00:00 2001 From: JamnedZ Date: Tue, 11 Oct 2022 16:38:03 +0700 Subject: [PATCH 43/50] Added installation of pyngrok if needed --- launch.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/launch.py b/launch.py index e1000f5..16627a0 100644 --- a/launch.py +++ b/launch.py @@ -104,6 +104,7 @@ def prepare_enviroment(): args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test') xformers = '--xformers' in args deepdanbooru = '--deepdanbooru' in args + ngrok = '--ngrok' in args try: commit = run(f"{git} rev-parse HEAD").strip() @@ -134,6 +135,9 @@ def prepare_enviroment(): if not is_installed("deepdanbooru") and deepdanbooru: run_pip("install git+https://github.com/KichangKim/DeepDanbooru.git@edf73df4cdaeea2cf00e9ac08bd8a9026b7a7b26#egg=deepdanbooru[tensorflow] tensorflow==2.10.0 tensorflow-io==0.27.0", "deepdanbooru") + if not is_installed("pyngrok") and ngrok: + run_pip("install pyngrok", "ngrok") + os.makedirs(dir_repos, exist_ok=True) git_clone("https://github.com/CompVis/stable-diffusion.git", repo_dir('stable-diffusion'), "Stable Diffusion", stable_diffusion_commit_hash) From 59925644480b6fd84f6bb84b4df7d4fbc6a0cce8 Mon Sep 17 00:00:00 2001 From: JamnedZ Date: Tue, 11 Oct 2022 16:40:27 +0700 Subject: [PATCH 44/50] Cleaned ngrok integration --- modules/ngrok.py | 15 +++++++++++++++ modules/shared.py | 1 + modules/ui.py | 5 +++++ 3 files changed, 21 insertions(+) create mode 100644 modules/ngrok.py diff --git a/modules/ngrok.py b/modules/ngrok.py new file mode 100644 index 0000000..17e6976 --- /dev/null +++ b/modules/ngrok.py @@ -0,0 +1,15 @@ +from pyngrok import ngrok, conf, exception + + +def connect(token, port): + if token == None: + token = 'None' + conf.get_default().auth_token = token + try: + public_url = ngrok.connect(port).public_url + except exception.PyngrokNgrokError: + print(f'Invalid ngrok authtoken, ngrok connection aborted.\n' + f'Your token: {token}, get the right one on https://dashboard.ngrok.com/get-started/your-authtoken') + else: + print(f'ngrok connected to localhost:{port}! URL: {public_url}\n' + 'You can use this link after the launch is complete.') \ No newline at end of file diff --git a/modules/shared.py b/modules/shared.py index 8753015..375e3af 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -38,6 +38,7 @@ parser.add_argument("--always-batch-cond-uncond", action='store_true', help="dis parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.") parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast") parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)") +parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None) parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer')) parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN')) parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN')) diff --git a/modules/ui.py b/modules/ui.py index fc0f3d3..f57f32d 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -51,6 +51,11 @@ if not cmd_opts.share and not cmd_opts.listen: gradio.utils.version_check = lambda: None gradio.utils.get_local_ip_address = lambda: '127.0.0.1' +if cmd_opts.ngrok != None: + import modules.ngrok as ngrok + print('ngrok authtoken detected, trying to connect...') + ngrok.connect(cmd_opts.ngrok, cmd_opts.port if cmd_opts.port != None else 7860) + def gr_show(visible=True): return {"visible": visible, "__type__": "update"} From a004d1a855311b0d7ff2976a4e31b0247ad9d1f6 Mon Sep 17 00:00:00 2001 From: JamnedZ Date: Tue, 11 Oct 2022 16:48:27 +0700 Subject: [PATCH 45/50] Added new line at the end of ngrok.py --- modules/ngrok.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/ngrok.py b/modules/ngrok.py index 17e6976..7d03a6d 100644 --- a/modules/ngrok.py +++ b/modules/ngrok.py @@ -12,4 +12,4 @@ def connect(token, port): f'Your token: {token}, get the right one on https://dashboard.ngrok.com/get-started/your-authtoken') else: print(f'ngrok connected to localhost:{port}! URL: {public_url}\n' - 'You can use this link after the launch is complete.') \ No newline at end of file + 'You can use this link after the launch is complete.') From 873efeed49bb5197a42da18272115b326c5d68f3 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 15:51:22 +0300 Subject: [PATCH 46/50] rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have --- modules/{hypernetwork => hypernetworks}/hypernetwork.py | 0 modules/{hypernetwork => hypernetworks}/ui.py | 2 +- modules/sd_hijack.py | 2 +- modules/sd_hijack_optimizations.py | 2 +- modules/shared.py | 2 +- modules/ui.py | 2 +- scripts/xy_grid.py | 2 +- webui.py | 2 +- 8 files changed, 7 insertions(+), 7 deletions(-) rename modules/{hypernetwork => hypernetworks}/hypernetwork.py (100%) rename modules/{hypernetwork => hypernetworks}/ui.py (92%) diff --git a/modules/hypernetwork/hypernetwork.py b/modules/hypernetworks/hypernetwork.py similarity index 100% rename from modules/hypernetwork/hypernetwork.py rename to modules/hypernetworks/hypernetwork.py diff --git a/modules/hypernetwork/ui.py b/modules/hypernetworks/ui.py similarity index 92% rename from modules/hypernetwork/ui.py rename to modules/hypernetworks/ui.py index f6d1d0a..811bc31 100644 --- a/modules/hypernetwork/ui.py +++ b/modules/hypernetworks/ui.py @@ -6,7 +6,7 @@ import gradio as gr import modules.textual_inversion.textual_inversion import modules.textual_inversion.preprocess from modules import sd_hijack, shared -from modules.hypernetwork import hypernetwork +from modules.hypernetworks import hypernetwork def create_hypernetwork(name): diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index f873049..f07ec04 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -37,7 +37,7 @@ def apply_optimizations(): def undo_optimizations(): - from modules.hypernetwork import hypernetwork + from modules.hypernetworks import hypernetwork ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index 27e571f..3349b9c 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -9,7 +9,7 @@ from ldm.util import default from einops import rearrange from modules import shared -from modules.hypernetwork import hypernetwork +from modules.hypernetworks import hypernetwork if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers: diff --git a/modules/shared.py b/modules/shared.py index 375e3af..1dc2ccf 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -14,7 +14,7 @@ import modules.sd_models import modules.styles import modules.devices as devices from modules import sd_samplers -from modules.hypernetwork import hypernetwork +from modules.hypernetworks import hypernetwork from modules.paths import models_path, script_path, sd_path sd_model_file = os.path.join(script_path, 'model.ckpt') diff --git a/modules/ui.py b/modules/ui.py index f57f32d..42e5d86 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -39,7 +39,7 @@ import modules.generation_parameters_copypaste from modules import prompt_parser from modules.images import save_image import modules.textual_inversion.ui -import modules.hypernetwork.ui +import modules.hypernetworks.ui # this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI mimetypes.init() diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py index 16918c9..cddb192 100644 --- a/scripts/xy_grid.py +++ b/scripts/xy_grid.py @@ -11,7 +11,7 @@ import modules.scripts as scripts import gradio as gr from modules import images -from modules.hypernetwork import hypernetwork +from modules.hypernetworks import hypernetwork from modules.processing import process_images, Processed, get_correct_sampler from modules.shared import opts, cmd_opts, state import modules.shared as shared diff --git a/webui.py b/webui.py index ba2156c..faa38a0 100644 --- a/webui.py +++ b/webui.py @@ -29,7 +29,7 @@ from modules import devices from modules import modelloader from modules.paths import script_path from modules.shared import cmd_opts -import modules.hypernetwork.hypernetwork +import modules.hypernetworks.hypernetwork modelloader.cleanup_models() modules.sd_models.setup_model() From b0583be0884cd17dafb408fd79b52b2a0a972563 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 15:54:34 +0300 Subject: [PATCH 47/50] more renames --- modules/hypernetworks/ui.py | 4 ++-- modules/ui.py | 4 ++-- webui.py | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/modules/hypernetworks/ui.py b/modules/hypernetworks/ui.py index 811bc31..e7540f4 100644 --- a/modules/hypernetworks/ui.py +++ b/modules/hypernetworks/ui.py @@ -13,7 +13,7 @@ def create_hypernetwork(name): fn = os.path.join(shared.cmd_opts.hypernetwork_dir, f"{name}.pt") assert not os.path.exists(fn), f"file {fn} already exists" - hypernet = modules.hypernetwork.hypernetwork.Hypernetwork(name=name) + hypernet = modules.hypernetworks.hypernetwork.Hypernetwork(name=name) hypernet.save(fn) shared.reload_hypernetworks() @@ -28,7 +28,7 @@ def train_hypernetwork(*args): try: sd_hijack.undo_optimizations() - hypernetwork, filename = modules.hypernetwork.hypernetwork.train_hypernetwork(*args) + hypernetwork, filename = modules.hypernetworks.hypernetwork.train_hypernetwork(*args) res = f""" Training {'interrupted' if shared.state.interrupted else 'finished'} at {hypernetwork.step} steps. diff --git a/modules/ui.py b/modules/ui.py index 42e5d86..ee333c3 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1111,7 +1111,7 @@ def create_ui(wrap_gradio_gpu_call): ) create_hypernetwork.click( - fn=modules.hypernetwork.ui.create_hypernetwork, + fn=modules.hypernetworks.ui.create_hypernetwork, inputs=[ new_hypernetwork_name, ], @@ -1164,7 +1164,7 @@ def create_ui(wrap_gradio_gpu_call): ) train_hypernetwork.click( - fn=wrap_gradio_gpu_call(modules.hypernetwork.ui.train_hypernetwork, extra_outputs=[gr.update()]), + fn=wrap_gradio_gpu_call(modules.hypernetworks.ui.train_hypernetwork, extra_outputs=[gr.update()]), _js="start_training_textual_inversion", inputs=[ train_hypernetwork_name, diff --git a/webui.py b/webui.py index faa38a0..338f58e 100644 --- a/webui.py +++ b/webui.py @@ -83,7 +83,7 @@ modules.scripts.load_scripts(os.path.join(script_path, "scripts")) shared.sd_model = modules.sd_models.load_model() shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model))) -shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork))) +shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetworks.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork))) def webui(): From 5766ce21abc1986c94d8bd3279b6f4d5205ba984 Mon Sep 17 00:00:00 2001 From: ClashSAN <98228077+ClashSAN@users.noreply.github.com> Date: Tue, 11 Oct 2022 13:20:03 +0000 Subject: [PATCH 48/50] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0e93876..a10faa0 100644 --- a/README.md +++ b/README.md @@ -69,7 +69,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web - also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2` - No token limit for prompts (original stable diffusion lets you use up to 75 tokens) - DeepDanbooru integration, creates danbooru style tags for anime prompts (add --deepdanbooru to commandline args) -- [xformers](https://github.com/mv-lab/swin2sr), major speed increase for select cards: (add --xformers to commandline args) +- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args) ## Installation and Running Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs. From 66b7d7584f0b44ce1316425808c27ca7df38293c Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 17:03:00 +0300 Subject: [PATCH 49/50] become even stricter with pickles no pickle shall pass thank you again, RyotaK --- modules/safe.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/modules/safe.py b/modules/safe.py index 0591746..20be16a 100644 --- a/modules/safe.py +++ b/modules/safe.py @@ -10,6 +10,7 @@ import torch import numpy import _codecs import zipfile +import re # PyTorch 1.13 and later have _TypedStorage renamed to TypedStorage @@ -54,11 +55,27 @@ class RestrictedUnpickler(pickle.Unpickler): raise pickle.UnpicklingError(f"global '{module}/{name}' is forbidden") +allowed_zip_names = ["archive/data.pkl", "archive/version"] +allowed_zip_names_re = re.compile(r"^archive/data/\d+$") + + +def check_zip_filenames(filename, names): + for name in names: + if name in allowed_zip_names: + continue + if allowed_zip_names_re.match(name): + continue + + raise Exception(f"bad file inside {filename}: {name}") + + def check_pt(filename): try: # new pytorch format is a zip file with zipfile.ZipFile(filename) as z: + check_zip_filenames(filename, z.namelist()) + with z.open('archive/data.pkl') as file: unpickler = RestrictedUnpickler(file) unpickler.load() From e0ee5bf703996b33e6d97aa36e0973ceedc88503 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Tue, 11 Oct 2022 17:08:03 +0300 Subject: [PATCH 50/50] add codeowners file so stop the great guys who are collaborating on the project from merging in PRs. --- CODEOWNERS | 1 + 1 file changed, 1 insertion(+) create mode 100644 CODEOWNERS diff --git a/CODEOWNERS b/CODEOWNERS new file mode 100644 index 0000000..935fedc --- /dev/null +++ b/CODEOWNERS @@ -0,0 +1 @@ +* @AUTOMATIC1111