Merge branch 'master' into 6866-fix-hires-prompt-matrix

README.md

@@ -104,8 +104,7 @@ Alternatively, use online services (like Google Colab):
 1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"
 2. Install [git](https://git-scm.com/download/win).
 3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
-4. Place stable diffusion checkpoint (`model.ckpt`) in the `models/Stable-diffusion` directory (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
-5. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
+4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
 
 ### Automatic Installation on Linux
 1. Install the dependencies:
@@ -121,7 +120,7 @@ sudo pacman -S wget git python3
 ```bash
 bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)
 ```
-
+3. Run `webui.sh`.
 ### Installation on Apple Silicon
 
 Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).

javascript/hints.js

@@ -8,16 +8,16 @@ titles = {
 	"DDIM": "Denoising Diffusion Implicit Models - best at inpainting",
 	"DPM adaptive": "Ignores step count - uses a number of steps determined by the CFG and resolution", 
 
-	"Batch count": "How many batches of images to create",
-	"Batch size": "How many image to create in a single batch",
+	"Batch count": "How many batches of images to create (has no impact on generation performance or VRAM usage)",
+	"Batch size": "How many image to create in a single batch (increases generation performance at cost of higher VRAM usage)",
     "CFG Scale": "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results",
     "Seed": "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result",
     "\u{1f3b2}\ufe0f": "Set seed to -1, which will cause a new random number to be used every time",
     "\u267b\ufe0f": "Reuse seed from last generation, mostly useful if it was randomed",
     "\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
     "\u{1f4c2}": "Open images output directory",
     "\u{1f4be}": "Save style",
-    "\U0001F5D1": "Clear prompt",
+    "\u{1f5d1}": "Clear prompt",
     "\u{1f4cb}": "Apply selected styles to current prompt",
     "\u{1f4d2}": "Paste available values into the field",
     "\u{1f3b4}": "Show extra networks",
@@ -66,8 +66,8 @@ titles = {
 
     "Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
 
-    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
-    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg],[prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
     "Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
 
     "Loopback": "Process an image, use it as an input, repeat.",

launch.py

@@ -242,7 +242,7 @@ def prepare_environment():
 
     sys.argv += shlex.split(commandline_args)
 
-    parser = argparse.ArgumentParser()
+    parser = argparse.ArgumentParser(add_help=False)
     parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default='config.json')
     args, _ = parser.parse_known_args(sys.argv)
 

modules/devices.py

@@ -1,21 +1,17 @@
-import sys, os, shlex
+import sys
 import contextlib
 import torch
 from modules import errors
-from packaging import version
+
+if sys.platform == "darwin":
+    from modules import mac_specific
 
 
-# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
-# check `getattr` and try it for compatibility
 def has_mps() -> bool:
-    if not getattr(torch, 'has_mps', False):
-        return False
-    try:
-        torch.zeros(1).to(torch.device("mps"))
-        return True
-    except Exception:
+    if sys.platform != "darwin":
         return False
-
+    else:
+        return mac_specific.has_mps
 
 def extract_device_id(args, name):
     for x in range(len(args)):
@@ -154,56 +150,3 @@ def test_for_nans(x, where):
     message += " Use --disable-nan-check commandline argument to disable this check."
 
     raise NansException(message)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
-orig_tensor_to = torch.Tensor.to
-def tensor_to_fix(self, *args, **kwargs):
-    if self.device.type != 'mps' and \
-       ((len(args) > 0 and isinstance(args[0], torch.device) and args[0].type == 'mps') or \
-       (isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps')):
-        self = self.contiguous()
-    return orig_tensor_to(self, *args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/80800 
-orig_layer_norm = torch.nn.functional.layer_norm
-def layer_norm_fix(*args, **kwargs):
-    if len(args) > 0 and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps':
-        args = list(args)
-        args[0] = args[0].contiguous()
-    return orig_layer_norm(*args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/90532
-orig_tensor_numpy = torch.Tensor.numpy
-def numpy_fix(self, *args, **kwargs):
-    if self.requires_grad:
-        self = self.detach()
-    return orig_tensor_numpy(self, *args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/89784
-orig_cumsum = torch.cumsum
-orig_Tensor_cumsum = torch.Tensor.cumsum
-def cumsum_fix(input, cumsum_func, *args, **kwargs):
-    if input.device.type == 'mps':
-        output_dtype = kwargs.get('dtype', input.dtype)
-        if output_dtype == torch.int64:
-            return cumsum_func(input.cpu(), *args, **kwargs).to(input.device)
-        elif cumsum_needs_bool_fix and output_dtype == torch.bool or cumsum_needs_int_fix and (output_dtype == torch.int8 or output_dtype == torch.int16):
-            return cumsum_func(input.to(torch.int32), *args, **kwargs).to(torch.int64)
-    return cumsum_func(input, *args, **kwargs)
-
-
-if has_mps():
-    if version.parse(torch.__version__) < version.parse("1.13"):
-        # PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working
-        torch.Tensor.to = tensor_to_fix
-        torch.nn.functional.layer_norm = layer_norm_fix
-        torch.Tensor.numpy = numpy_fix
-    elif version.parse(torch.__version__) > version.parse("1.13.1"):
-        cumsum_needs_int_fix = not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.ShortTensor([1,1]).to(torch.device("mps")).cumsum(0))
-        cumsum_needs_bool_fix = not torch.BoolTensor([True,True]).to(device=torch.device("mps"), dtype=torch.int64).equal(torch.BoolTensor([True,False]).to(torch.device("mps")).cumsum(0))
-        torch.cumsum = lambda input, *args, **kwargs: ( cumsum_fix(input, orig_cumsum, *args, **kwargs) )
-        torch.Tensor.cumsum = lambda self, *args, **kwargs: ( cumsum_fix(self, orig_Tensor_cumsum, *args, **kwargs) )

modules/esrgan_model_arch.py

@@ -1,5 +1,6 @@
 # this file is adapted from https://github.com/victorca25/iNNfer
 
+from collections import OrderedDict
 import math
 import functools
 import torch

modules/extensions.py

@@ -2,6 +2,7 @@
 import sys
 import traceback
 
+import time
 import git
 
 from modules import paths, shared
@@ -25,6 +26,7 @@ def __init__(self, name, path, enabled=True, is_builtin=False):
         self.status = ''
         self.can_update = False
         self.is_builtin = is_builtin
+        self.version = ''
 
         repo = None
         try:
@@ -40,6 +42,10 @@ def __init__(self, name, path, enabled=True, is_builtin=False):
             try:
                 self.remote = next(repo.remote().urls, None)
                 self.status = 'unknown'
+                head = repo.head.commit
+                ts = time.asctime(time.gmtime(repo.head.commit.committed_date))
+                self.version = f'{head.hexsha[:8]} ({ts})'
+
             except Exception:
                 self.remote = None
 

modules/generation_parameters_copypaste.py

@@ -74,8 +74,8 @@ def image_from_url_text(filedata):
     return image
 
 
-def add_paste_fields(tabname, init_img, fields):
-    paste_fields[tabname] = {"init_img": init_img, "fields": fields}
+def add_paste_fields(tabname, init_img, fields, override_settings_component=None):
+    paste_fields[tabname] = {"init_img": init_img, "fields": fields, "override_settings_component": override_settings_component}
 
     # backwards compatibility for existing extensions
     import modules.ui
@@ -110,6 +110,7 @@ def connect_paste_params_buttons():
     for binding in registered_param_bindings:
         destination_image_component = paste_fields[binding.tabname]["init_img"]
         fields = paste_fields[binding.tabname]["fields"]
+        override_settings_component = binding.override_settings_component or paste_fields[binding.tabname]["override_settings_component"]
 
         destination_width_component = next(iter([field for field, name in fields if name == "Size-1"] if fields else []), None)
         destination_height_component = next(iter([field for field, name in fields if name == "Size-2"] if fields else []), None)
@@ -130,7 +131,7 @@ def connect_paste_params_buttons():
             )
 
         if binding.source_text_component is not None and fields is not None:
-            connect_paste(binding.paste_button, fields, binding.source_text_component, binding.override_settings_component, binding.tabname)
+            connect_paste(binding.paste_button, fields, binding.source_text_component, override_settings_component, binding.tabname)
 
         if binding.source_tabname is not None and fields is not None:
             paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] + (["Seed"] if shared.opts.send_seed else [])

modules/hashes.py

@@ -4,6 +4,7 @@
 
 import filelock
 
+from modules import shared
 from modules.paths import data_path
 
 
@@ -68,6 +69,9 @@ def sha256(filename, title):
     if sha256_value is not None:
         return sha256_value
 
+    if shared.cmd_opts.no_hashing:
+        return None
+
     print(f"Calculating sha256 for {filename}: ", end='')
     sha256_value = calculate_sha256(filename)
     print(f"{sha256_value}")

modules/hypernetworks/hypernetwork.py

@@ -307,7 +307,7 @@ def load(self, filename):
     def shorthash(self):
         sha256 = hashes.sha256(self.filename, f'hypernet/{self.name}')
 
-        return sha256[0:10]
+        return sha256[0:10] if sha256 else None
 
 
 def list_hypernetworks(path):
@@ -380,8 +380,8 @@ def apply_single_hypernetwork(hypernetwork, context_k, context_v, layer=None):
         layer.hyper_k = hypernetwork_layers[0]
         layer.hyper_v = hypernetwork_layers[1]
 
-    context_k = hypernetwork_layers[0](context_k)
-    context_v = hypernetwork_layers[1](context_v)
+    context_k = devices.cond_cast_unet(hypernetwork_layers[0](devices.cond_cast_float(context_k)))
+    context_v = devices.cond_cast_unet(hypernetwork_layers[1](devices.cond_cast_float(context_v)))
     return context_k, context_v
 
 

modules/images.py

@@ -16,8 +16,9 @@
 from fonts.ttf import Roboto
 import string
 import json
+import hashlib
 
-from modules import sd_samplers, shared, script_callbacks
+from modules import sd_samplers, shared, script_callbacks, errors
 from modules.shared import opts, cmd_opts
 
 LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
@@ -130,7 +131,7 @@ def __init__(self, text='', is_active=True):
         self.size = None
 
 
-def draw_grid_annotations(im, width, height, hor_texts, ver_texts):
+def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
     def wrap(drawing, text, font, line_length):
         lines = ['']
         for word in text.split():
@@ -194,32 +195,35 @@ def draw_texts(drawing, draw_x, draw_y, lines, initial_fnt, initial_fontsize):
             line.allowed_width = allowed_width
 
     hor_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing for lines in hor_texts]
-    ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in
-                        ver_texts]
+    ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in ver_texts]
 
     pad_top = 0 if sum(hor_text_heights) == 0 else max(hor_text_heights) + line_spacing * 2
 
-    result = Image.new("RGB", (im.width + pad_left, im.height + pad_top), "white")
-    result.paste(im, (pad_left, pad_top))
+    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), "white")
+
+    for row in range(rows):
+        for col in range(cols):
+            cell = im.crop((width * col, height * row, width * (col+1), height * (row+1)))
+            result.paste(cell, (pad_left + (width + margin) * col, pad_top + (height + margin) * row))
 
     d = ImageDraw.Draw(result)
 
     for col in range(cols):
-        x = pad_left + width * col + width / 2
+        x = pad_left + (width + margin) * col + width / 2
         y = pad_top / 2 - hor_text_heights[col] / 2
 
         draw_texts(d, x, y, hor_texts[col], fnt, fontsize)
 
     for row in range(rows):
         x = pad_left / 2
-        y = pad_top + height * row + height / 2 - ver_text_heights[row] / 2
+        y = pad_top + (height + margin) * row + height / 2 - ver_text_heights[row] / 2
 
         draw_texts(d, x, y, ver_texts[row], fnt, fontsize)
 
     return result
 
 
-def draw_prompt_matrix(im, width, height, all_prompts):
+def draw_prompt_matrix(im, width, height, all_prompts, margin=0):
     prompts = all_prompts[1:]
     boundary = math.ceil(len(prompts) / 2)
 
@@ -229,7 +233,7 @@ def draw_prompt_matrix(im, width, height, all_prompts):
     hor_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_horiz)] for pos in range(1 << len(prompts_horiz))]
     ver_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_vert)] for pos in range(1 << len(prompts_vert))]
 
-    return draw_grid_annotations(im, width, height, hor_texts, ver_texts)
+    return draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin)
 
 
 def resize_image(resize_mode, im, width, height, upscaler_name=None):
@@ -340,6 +344,7 @@ class FilenameGenerator:
         'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
         'datetime': lambda self, *args: self.datetime(*args),  # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
         'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
+        'prompt_hash': lambda self: hashlib.sha256(self.prompt.encode()).hexdigest()[0:8],
         'prompt': lambda self: sanitize_filename_part(self.prompt),
         'prompt_no_styles': lambda self: self.prompt_no_style(),
         'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False),
@@ -548,6 +553,8 @@ def _atomically_save_image(image_to_save, filename_without_extension, extension)
         elif extension.lower() in (".jpg", ".jpeg", ".webp"):
             if image_to_save.mode == 'RGBA':
                 image_to_save = image_to_save.convert("RGB")
+            elif image_to_save.mode == 'I;16':
+                image_to_save = image_to_save.point(lambda p: p * 0.0038910505836576).convert("RGB" if extension.lower() == ".webp" else "L")
 
             image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality)
 
@@ -570,17 +577,19 @@ def _atomically_save_image(image_to_save, filename_without_extension, extension)
 
     image.already_saved_as = fullfn
 
-    target_side_length = 4000
-    oversize = image.width > target_side_length or image.height > target_side_length
-    if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > 4 * 1024 * 1024):
+    oversize = image.width > opts.target_side_length or image.height > opts.target_side_length
+    if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > opts.img_downscale_threshold * 1024 * 1024):
         ratio = image.width / image.height
 
         if oversize and ratio > 1:
-            image = image.resize((target_side_length, image.height * target_side_length // image.width), LANCZOS)
+            image = image.resize((opts.target_side_length, image.height * opts.target_side_length // image.width), LANCZOS)
         elif oversize:
-            image = image.resize((image.width * target_side_length // image.height, target_side_length), LANCZOS)
+            image = image.resize((image.width * opts.target_side_length // image.height, opts.target_side_length), LANCZOS)
 
-        _atomically_save_image(image, fullfn_without_extension, ".jpg")
+        try:
+            _atomically_save_image(image, fullfn_without_extension, ".jpg")
+        except Exception as e:
+            errors.display(e, "saving image as downscaled JPG")
 
     if opts.save_txt and info is not None:
         txt_fullfn = f"{fullfn_without_extension}.txt"