test

CODEOWNERS

+*       @AUTOMATIC1111

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/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.
@@ -116,13 +119,17 @@ 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.
+- InvokeAI, lstein - Cross Attention layer optimization - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
 - Rinon Gal - Textual Inversion - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
 - 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)

artists.csv

@@ -1045,7 +1045,6 @@ Bakemono Zukushi,0.67051035,anime
 Lucy Madox Brown,0.67032814,fineart
 Paul Wonner,0.6700563,scribbles
 Guido Borelli Da Caluso,0.66966087,digipa-high-impact
-Guido Borelli da Caluso,0.66966087,digipa-high-impact
 Emil Alzamora,0.5844039,nudity
 Heinrich Brocksieper,0.64469147,fineart
 Dan Smith,0.669563,digipa-high-impact

environment-wsl2.yaml

@@ -3,9 +3,9 @@ channels:
   - pytorch
   - defaults
 dependencies:
-  - python=3.8.5
-  - pip=20.3
+  - python=3.10
+  - pip=22.2.2
   - cudatoolkit=11.3
-  - pytorch=1.11.0
-  - torchvision=0.12.0
-  - numpy=1.19.2
+  - pytorch=1.12.1
+  - torchvision=0.13.1
+  - numpy=1.23.1
\ No newline at end of file

javascript/edit-attention.js

@@ -25,6 +25,7 @@ addEventListener('keydown', (event) => {
 	} else {
 		end = target.value.slice(selectionEnd + 1).indexOf(")") + 1;
 		weight = parseFloat(target.value.slice(selectionEnd + 1, selectionEnd + 1 + end));
+		if (isNaN(weight)) return;
 		if (event.key == minus) weight -= 0.1;
 		if (event.key == plus) weight += 0.1;
 
@@ -38,4 +39,7 @@ addEventListener('keydown', (event) => {
 		target.selectionStart = selectionStart;
 		target.selectionEnd = selectionEnd;
 	}
+	// Since we've modified a Gradio Textbox component manually, we need to simulate an `input` DOM event to ensure its
+	// internal Svelte data binding remains in sync.
+	target.dispatchEvent(new Event("input", { bubbles: true }));
 });

javascript/hints.js

@@ -80,7 +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.",
+    "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 behaving in an unethical manner.",
 }
 
 

javascript/ui.js

@@ -101,7 +101,8 @@ function create_tab_index_args(tabId, args){
 }
 
 function get_extras_tab_index(){
-    return create_tab_index_args('mode_extras', arguments)
+    const [,,...args] = [...arguments]
+    return [get_tab_index('mode_extras'), get_tab_index('extras_resize_mode'), ...args]
 }
 
 function create_submit_args(args){

modules/deepbooru.py

 import os.path
 from concurrent.futures import ProcessPoolExecutor
-from multiprocessing import get_context
+import multiprocessing
+import time
 
+def get_deepbooru_tags(pil_image):
+    """
+    This method is for running only one image at a time for simple use.  Used to the img2img interrogate.
+    """
+    from modules import shared  # prevents circular reference
+    create_deepbooru_process(shared.opts.interrogate_deepbooru_score_threshold, shared.opts.deepbooru_sort_alpha)
+    shared.deepbooru_process_return["value"] = -1
+    shared.deepbooru_process_queue.put(pil_image)
+    while shared.deepbooru_process_return["value"] == -1:
+        time.sleep(0.2)
+    tags = shared.deepbooru_process_return["value"]
+    release_process()
+    return tags
 
-def _load_tf_and_return_tags(pil_image, threshold):
+
+def deepbooru_process(queue, deepbooru_process_return, threshold, alpha_sort):
+    model, tags = get_deepbooru_tags_model()
+    while True: # while process is running, keep monitoring queue for new image
+        pil_image = queue.get()
+        if pil_image == "QUIT":
+            break
+        else:
+            deepbooru_process_return["value"] = get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort)
+
+
+def create_deepbooru_process(threshold, alpha_sort):
+    """
+    Creates deepbooru process.  A queue is created to send images into the process.  This enables multiple images
+    to be processed in a row without reloading the model or creating a new process.  To return the data, a shared
+    dictionary is created to hold the tags created.  To wait for tags to be returned, a value of -1 is assigned
+    to the dictionary and the method adding the image to the queue should wait for this value to be updated with
+    the tags.
+    """
+    from modules import shared  # prevents circular reference
+    shared.deepbooru_process_manager = multiprocessing.Manager()
+    shared.deepbooru_process_queue = shared.deepbooru_process_manager.Queue()
+    shared.deepbooru_process_return = shared.deepbooru_process_manager.dict()
+    shared.deepbooru_process_return["value"] = -1
+    shared.deepbooru_process = multiprocessing.Process(target=deepbooru_process, args=(shared.deepbooru_process_queue, shared.deepbooru_process_return, threshold, alpha_sort))
+    shared.deepbooru_process.start()
+
+
+def release_process():
+    """
+    Stops the deepbooru process to return used memory
+    """
+    from modules import shared  # prevents circular reference
+    shared.deepbooru_process_queue.put("QUIT")
+    shared.deepbooru_process.join()
+    shared.deepbooru_process_queue = None
+    shared.deepbooru_process = None
+    shared.deepbooru_process_return = None
+    shared.deepbooru_process_manager = None
+
+def get_deepbooru_tags_model():
     import deepdanbooru as dd
     import tensorflow as tf
     import numpy as np
-
     this_folder = os.path.dirname(__file__)
     model_path = os.path.abspath(os.path.join(this_folder, '..', 'models', 'deepbooru'))
     if not os.path.exists(os.path.join(model_path, 'project.json')):
         # there is no point importing these every time
         import zipfile
         from basicsr.utils.download_util import load_file_from_url
-        load_file_from_url(r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip",
-                           model_path)
+        load_file_from_url(
+            r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip",
+            model_path)
         with zipfile.ZipFile(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"), "r") as zip_ref:
             zip_ref.extractall(model_path)
         os.remove(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"))
@@ -24,7 +78,13 @@ def _load_tf_and_return_tags(pil_image, threshold):
     model = dd.project.load_model_from_project(
         model_path, compile_model=True
     )
+    return model, tags
+
 
+def get_deepbooru_tags_from_model(model, tags, pil_image, threshold, alpha_sort):
+    import deepdanbooru as dd
+    import tensorflow as tf
+    import numpy as np
     width = model.input_shape[2]
     height = model.input_shape[1]
     image = np.array(pil_image)
@@ -46,28 +106,27 @@ def _load_tf_and_return_tags(pil_image, threshold):
 
     for i, tag in enumerate(tags):
         result_dict[tag] = y[i]
-    result_tags_out = []
+
+    unsorted_tags_in_theshold = []
     result_tags_print = []
     for tag in tags:
         if result_dict[tag] >= threshold:
             if tag.startswith("rating:"):
                 continue
-            result_tags_out.append(tag)
+            unsorted_tags_in_theshold.append((result_dict[tag], tag))
             result_tags_print.append(f'{result_dict[tag]} {tag}')
 
-    print('\n'.join(sorted(result_tags_print, reverse=True)))
-
-    return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ')
-
+    # sort tags
+    result_tags_out = []
+    sort_ndx = 0
+    if alpha_sort:
+        sort_ndx = 1
 
-def subprocess_init_no_cuda():
-    import os
-    os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+    # sort by reverse by likelihood and normal for alpha
+    unsorted_tags_in_theshold.sort(key=lambda y: y[sort_ndx], reverse=(not alpha_sort))
+    for weight, tag in unsorted_tags_in_theshold:
+        result_tags_out.append(tag)
 
+    print('\n'.join(sorted(result_tags_print, reverse=True)))
 
-def get_deepbooru_tags(pil_image, threshold=0.5):
-    context = get_context('spawn')
-    with ProcessPoolExecutor(initializer=subprocess_init_no_cuda, mp_context=context) as executor:
-        f = executor.submit(_load_tf_and_return_tags, pil_image, threshold, )
-        ret = f.result()  # will rethrow any exceptions
-    return ret
\ No newline at end of file
+    return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ')

modules/extras.py

+import math
 import os
 
 import numpy as np
@@ -19,7 +20,7 @@ import gradio as gr
 cached_images = {}
 
 
-def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility):
+def run_extras(extras_mode, resize_mode, image, image_folder, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility):
     devices.torch_gc()
 
     imageArr = []
@@ -67,8 +68,13 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v
             info += f"CodeFormer w: {round(codeformer_weight, 2)}, CodeFormer visibility:{round(codeformer_visibility, 2)}\n"
             image = res
 
+        if resize_mode == 1:
+            upscaling_resize = max(upscaling_resize_w/image.width, upscaling_resize_h/image.height)
+            crop_info = " (crop)" if upscaling_crop else ""
+            info += f"Resize to: {upscaling_resize_w:g}x{upscaling_resize_h:g}{crop_info}\n"
+
         if upscaling_resize != 1.0:
-            def upscale(image, scaler_index, resize):
+            def upscale(image, scaler_index, resize, mode, resize_w, resize_h, crop):
                 small = image.crop((image.width // 2, image.height // 2, image.width // 2 + 10, image.height // 2 + 10))
                 pixels = tuple(np.array(small).flatten().tolist())
                 key = (resize, scaler_index, image.width, image.height, gfpgan_visibility, codeformer_visibility, codeformer_weight) + pixels
@@ -77,15 +83,19 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v
                 if c is None:
                     upscaler = shared.sd_upscalers[scaler_index]
                     c = upscaler.scaler.upscale(image, resize, upscaler.data_path)
+                    if mode == 1 and crop:
+                        cropped = Image.new("RGB", (resize_w, resize_h))
+                        cropped.paste(c, box=(resize_w // 2 - c.width // 2, resize_h // 2 - c.height // 2))
+                        c = cropped
                     cached_images[key] = c
 
                 return c
 
             info += f"Upscale: {round(upscaling_resize, 3)}, model:{shared.sd_upscalers[extras_upscaler_1].name}\n"
-            res = upscale(image, extras_upscaler_1, upscaling_resize)
+            res = upscale(image, extras_upscaler_1, upscaling_resize, resize_mode, upscaling_resize_w, upscaling_resize_h, upscaling_crop)
 
             if extras_upscaler_2 != 0 and extras_upscaler_2_visibility > 0:
-                res2 = upscale(image, extras_upscaler_2, upscaling_resize)
+                res2 = upscale(image, extras_upscaler_2, upscaling_resize, resize_mode, upscaling_resize_w, upscaling_resize_h, upscaling_crop)
                 info += f"Upscale: {round(upscaling_resize, 3)}, visibility: {round(extras_upscaler_2_visibility, 3)}, model:{shared.sd_upscalers[extras_upscaler_2].name}\n"
                 res = Image.blend(res, res2, extras_upscaler_2_visibility)
 
@@ -190,7 +200,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, interp_method, int
             theta_0[key] = theta_func(theta_0[key], theta_1[key], (float(1.0) - interp_amount))  # Need to reverse the interp_amount to match the desired mix ration in the merged checkpoint
             if save_as_half:
                 theta_0[key] = theta_0[key].half()
-    
+
     for key in theta_1.keys():
         if 'model' in key and key not in theta_0:
             theta_0[key] = theta_1[key]

modules/hypernetworks/hypernetwork.py

@@ -14,6 +14,7 @@ import torch
 from torch import einsum
 from einops import rearrange, repeat
 import modules.textual_inversion.dataset
+from modules.textual_inversion.learn_schedule import LearnSchedule
 
 
 class HypernetworkModule(torch.nn.Module):
@@ -42,7 +43,7 @@ class Hypernetwork:
     filename = None
     name = None
 
-    def __init__(self, name=None):
+    def __init__(self, name=None, enable_sizes=None):
         self.filename = None
         self.name = name
         self.layers = {}
@@ -50,7 +51,7 @@ class Hypernetwork:
         self.sd_checkpoint = None
         self.sd_checkpoint_name = None
 
-        for size in [320, 640, 768, 1280]:
+        for size in enable_sizes or []:
             self.layers[size] = (HypernetworkModule(size), HypernetworkModule(size))
 
     def weights(self):
@@ -119,6 +120,17 @@ def load_hypernetwork(filename):
         shared.loaded_hypernetwork = None
 
 
+def find_closest_hypernetwork_name(search: str):
+    if not search:
+        return None
+    search = search.lower()
+    applicable = [name for name in shared.hypernetworks if search in name.lower()]
+    if not applicable:
+        return None
+    applicable = sorted(applicable, key=lambda name: len(name))
+    return applicable[0]
+
+
 def apply_hypernetwork(hypernetwork, context, layer=None):
     hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
 
@@ -163,7 +175,7 @@ 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'
+    assert hypernetwork_name, 'hypernetwork not selected'
 
     path = shared.hypernetworks.get(hypernetwork_name, None)
     shared.loaded_hypernetwork = Hypernetwork()
@@ -175,6 +187,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
     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)
+    unload = shared.opts.unload_models_when_training
 
     if save_hypernetwork_every > 0:
         hypernetwork_dir = os.path.join(log_directory, "hypernetworks")
@@ -188,19 +201,19 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
     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, width=512, height=512, repeats=1, 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, include_cond=True)
+
+    if unload:
+        shared.sd_model.cond_stage_model.to(devices.cpu)
+        shared.sd_model.first_stage_model.to(devices.cpu)
 
     hypernetwork = shared.loaded_hypernetwork
     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 = "<none>"
@@ -210,22 +223,34 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
     if ititial_step > steps:
         return hypernetwork, filename
 
+    schedules = iter(LearnSchedule(learn_rate, steps, ititial_step))
+    (learn_rate, end_step) = next(schedules)
+    print(f'Training at rate of {learn_rate} until step {end_step}')
+
+    optimizer = torch.optim.AdamW(weights, lr=learn_rate)
+
     pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
-    for i, (x, text) in pbar:
+    for i, (x, text, cond) in pbar:
         hypernetwork.step = i + ititial_step
 
-        if hypernetwork.step > steps:
-            break
+        if hypernetwork.step > end_step:
+            try:
+                (learn_rate, end_step) = next(schedules)
+            except Exception:
+                break
+            tqdm.tqdm.write(f'Training at rate of {learn_rate} until step {end_step}')
+            for pg in optimizer.param_groups:
+                pg['lr'] = learn_rate
 
         if shared.state.interrupted:
             break
 
         with torch.autocast("cuda"):
-            c = cond_model([text])
-
+            cond = cond.to(devices.device)
             x = x.to(devices.device)
-            loss = shared.sd_model(x.unsqueeze(0), c)[0]
+            loss = shared.sd_model(x.unsqueeze(0), cond)[0]
             del x
+            del cond
 
             losses[hypernetwork.step % losses.shape[0]] = loss.item()
 
@@ -244,6 +269,10 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
 
             preview_text = text if preview_image_prompt == "" else preview_image_prompt
 
+            optimizer.zero_grad()
+            shared.sd_model.cond_stage_model.to(devices.device)
+            shared.sd_model.first_stage_model.to(devices.device)
+
             p = processing.StableDiffusionProcessingTxt2Img(
                 sd_model=shared.sd_model,
                 prompt=preview_text,
@@ -255,6 +284,10 @@ def train_hypernetwork(hypernetwork_name, learn_rate, data_root, log_directory,
             processed = processing.process_images(p)
             image = processed.images[0]
 
+            if unload:
+                shared.sd_model.cond_stage_model.to(devices.cpu)
+                shared.sd_model.first_stage_model.to(devices.cpu)
+
             shared.state.current_image = image
             image.save(last_saved_image)
 

modules/hypernetworks/ui.py

@@ -5,15 +5,15 @@ import gradio as gr
 
 import modules.textual_inversion.textual_inversion
 import modules.textual_inversion.preprocess
-from modules import sd_hijack, shared
+from modules import sd_hijack, shared, devices
 from modules.hypernetworks import hypernetwork
 
 
-def create_hypernetwork(name):
+def create_hypernetwork(name, enable_sizes):
     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.hypernetworks.hypernetwork.Hypernetwork(name=name)
+    hypernet = modules.hypernetworks.hypernetwork.Hypernetwork(name=name, enable_sizes=[int(x) for x in enable_sizes])
     hypernet.save(fn)
 
     shared.reload_hypernetworks()
@@ -25,6 +25,8 @@ def train_hypernetwork(*args):
 
     initial_hypernetwork = shared.loaded_hypernetwork
 
+    assert not shared.cmd_opts.lowvram, 'Training models with lowvram is not possible'
+
     try:
         sd_hijack.undo_optimizations()
 
@@ -39,5 +41,7 @@ Hypernetwork saved to {html.escape(filename)}
         raise
     finally:
         shared.loaded_hypernetwork = initial_hypernetwork
+        shared.sd_model.cond_stage_model.to(devices.device)
+        shared.sd_model.first_stage_model.to(devices.device)
         sd_hijack.apply_optimizations()
 

modules/images_history.py

@@ -136,7 +136,7 @@ def show_images_history(gr, opts, tabname, run_pnginfo, switch_dict):
         
 def create_history_tabs(gr, opts, run_pnginfo, switch_dict):
     with gr.Blocks(analytics_enabled=False) as images_history:
-        with gr.Tabs() as tabs:            
+        with gr.Tabs() as tabs:
             with gr.Tab("txt2img history"):
                 with gr.Blocks(analytics_enabled=False) as images_history_txt2img:   
                     show_images_history(gr, opts, "txt2img", run_pnginfo, switch_dict) 

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()

modules/sd_hijack.py

@@ -10,6 +10,7 @@ from torch.nn.functional import silu
 import modules.textual_inversion.textual_inversion
 from modules import prompt_parser, devices, sd_hijack_optimizations, shared
 from modules.shared import opts, device, cmd_opts
+from modules.sd_hijack_optimizations import invokeAI_mps_available
 
 import ldm.modules.attention
 import ldm.modules.diffusionmodules.model
@@ -30,8 +31,16 @@ def apply_optimizations():
     elif cmd_opts.opt_split_attention_v1:
         print("Applying v1 cross attention optimization.")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
+    elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention_invokeai or not torch.cuda.is_available()):
+        if not invokeAI_mps_available and shared.device.type == 'mps':
+            print("The InvokeAI cross attention optimization for MPS requires the psutil package which is not installed.")
+            print("Applying v1 cross attention optimization.")
+            ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
+        else:
+            print("Applying cross attention optimization (InvokeAI).")
+            ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_invokeAI
     elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
-        print("Applying cross attention optimization.")
+        print("Applying cross attention optimization (Doggettx).")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
 
@@ -312,7 +321,17 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
                         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])
+            tokens = []
+            multipliers = []
+            for j in range(len(remade_batch_tokens)):
+                if len(remade_batch_tokens[j]) > 0:
+                    tokens.append(remade_batch_tokens[j][:75])
+                    multipliers.append(batch_multipliers[j][:75])
+                else:
+                    tokens.append([self.wrapped.tokenizer.eos_token_id] * 75)
+                    multipliers.append([1.0] * 75)
+
+            z1 = self.process_tokens(tokens, multipliers)
             z = z1 if z is None else torch.cat((z, z1), axis=-2)
             
             remade_batch_tokens = rem_tokens

modules/sd_hijack_optimizations.py

 import math
 import sys
 import traceback
+import importlib
 
 import torch
 from torch import einsum
@@ -116,6 +117,102 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
 
     return self.to_out(r2)
 
+
+def check_for_psutil():
+    try:
+        spec = importlib.util.find_spec('psutil')
+        return spec is not None
+    except ModuleNotFoundError:
+        return False
+
+invokeAI_mps_available = check_for_psutil()
+
+# -- Taken from https://github.com/invoke-ai/InvokeAI --
+if invokeAI_mps_available:
+    import psutil
+    mem_total_gb = psutil.virtual_memory().total // (1 << 30)
+
+def einsum_op_compvis(q, k, v):
+    s = einsum('b i d, b j d -> b i j', q, k)
+    s = s.softmax(dim=-1, dtype=s.dtype)
+    return einsum('b i j, b j d -> b i d', s, v)
+
+def einsum_op_slice_0(q, k, v, slice_size):
+    r = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
+    for i in range(0, q.shape[0], slice_size):
+        end = i + slice_size
+        r[i:end] = einsum_op_compvis(q[i:end], k[i:end], v[i:end])
+    return r
+
+def einsum_op_slice_1(q, k, v, slice_size):
+    r = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
+    for i in range(0, q.shape[1], slice_size):
+        end = i + slice_size
+        r[:, i:end] = einsum_op_compvis(q[:, i:end], k, v)
+    return r
+
+def einsum_op_mps_v1(q, k, v):
+    if q.shape[1] <= 4096: # (512x512) max q.shape[1]: 4096
+        return einsum_op_compvis(q, k, v)
+    else:
+        slice_size = math.floor(2**30 / (q.shape[0] * q.shape[1]))
+        return einsum_op_slice_1(q, k, v, slice_size)
+
+def einsum_op_mps_v2(q, k, v):
+    if mem_total_gb > 8 and q.shape[1] <= 4096:
+        return einsum_op_compvis(q, k, v)
+    else:
+        return einsum_op_slice_0(q, k, v, 1)
+
+def einsum_op_tensor_mem(q, k, v, max_tensor_mb):
+    size_mb = q.shape[0] * q.shape[1] * k.shape[1] * q.element_size() // (1 << 20)
+    if size_mb <= max_tensor_mb:
+        return einsum_op_compvis(q, k, v)
+    div = 1 << int((size_mb - 1) / max_tensor_mb).bit_length()
+    if div <= q.shape[0]:
+        return einsum_op_slice_0(q, k, v, q.shape[0] // div)
+    return einsum_op_slice_1(q, k, v, max(q.shape[1] // div, 1))
+
+def einsum_op_cuda(q, k, v):
+    stats = torch.cuda.memory_stats(q.device)
+    mem_active = stats['active_bytes.all.current']
+    mem_reserved = stats['reserved_bytes.all.current']
+    mem_free_cuda, _ = torch.cuda.mem_get_info(q.device)
+    mem_free_torch = mem_reserved - mem_active
+    mem_free_total = mem_free_cuda + mem_free_torch
+    # Divide factor of safety as there's copying and fragmentation
+    return self.einsum_op_tensor_mem(q, k, v, mem_free_total / 3.3 / (1 << 20))
+
+def einsum_op(q, k, v):
+    if q.device.type == 'cuda':
+        return einsum_op_cuda(q, k, v)
+
+    if q.device.type == 'mps':
+        if mem_total_gb >= 32:
+            return einsum_op_mps_v1(q, k, v)
+        return einsum_op_mps_v2(q, k, v)
+
+    # Smaller slices are faster due to L2/L3/SLC caches.
+    # Tested on i7 with 8MB L3 cache.
+    return einsum_op_tensor_mem(q, k, v, 32)
+
+def split_cross_attention_forward_invokeAI(self, x, context=None, mask=None):
+    h = self.heads
+
+    q = self.to_q(x)
+    context = default(context, x)
+
+    context_k, context_v = hypernetwork.apply_hypernetwork(shared.loaded_hypernetwork, context)
+    k = self.to_k(context_k) * self.scale
+    v = 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, k, v))
+    r = einsum_op(q, k, v)
+    return self.to_out(rearrange(r, '(b h) n d -> b n (h d)', h=h))
+
+# -- End of code from https://github.com/invoke-ai/InvokeAI --
+
 def xformers_attention_forward(self, x, context=None, mask=None):
     h = self.heads
     q_in = self.to_q(x)

modules/shared.py

@@ -50,9 +50,10 @@ parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with
 parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
 parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
 parser.add_argument("--deepdanbooru", action='store_true', help="enable deepdanbooru interrogator")
-parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
-parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
+parser.add_argument("--opt-split-attention", action='store_true', help="force-enables Doggettx's cross-attention layer optimization. By default, it's on for torch cuda.")
+parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
 parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
+parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
 parser.add_argument("--use-cpu", nargs='+',choices=['SD', 'GFPGAN', 'BSRGAN', 'ESRGAN', 'SCUNet', 'CodeFormer'], help="use CPU as torch device for specified modules", default=[])
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
@@ -85,6 +86,7 @@ parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
 xformers_available = False
 config_filename = cmd_opts.ui_settings_file
 
+os.makedirs(cmd_opts.hypernetwork_dir, exist_ok=True)
 hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
 loaded_hypernetwork = None
 
@@ -227,6 +229,10 @@ options_templates.update(options_section(('system', "System"), {
     "multiple_tqdm": OptionInfo(True, "Add a second progress bar to the console that shows progress for an entire job."),
 }))
 
+options_templates.update(options_section(('training', "Training"), {
+    "unload_models_when_training": OptionInfo(False, "Unload VAE and CLIP from VRAM when training"),
+}))
+
 options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, show_on_main_page=True),
     "sd_hypernetwork": OptionInfo("None", "Stable Diffusion finetune hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}),
@@ -249,8 +255,8 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
     "interrogate_clip_num_beams": OptionInfo(1, "Interrogate: num_beams for BLIP", gr.Slider, {"minimum": 1, "maximum": 16, "step": 1}),
     "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}),
+    "deepbooru_sort_alpha": OptionInfo(True, "Interrogate: deepbooru sort alphabetically"),
 }))
 
 options_templates.update(options_section(('ui', "User interface"), {

modules/textual_inversion/dataset.py

@@ -8,14 +8,14 @@ from torchvision import transforms
 
 import random
 import tqdm
-from modules import devices
+from modules import devices, shared
 import re
 
 re_tag = re.compile(r"[a-zA-Z][_\w\d()]+")
 
 
 class PersonalizedBase(Dataset):
-    def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None):
+    def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None, include_cond=False):
 
         self.placeholder_token = placeholder_token
 
@@ -32,12 +32,15 @@ class PersonalizedBase(Dataset):
 
         assert data_root, 'dataset directory not specified'
 
+        cond_model = shared.sd_model.cond_stage_model
+
         self.image_paths = [os.path.join(data_root, file_path) for file_path in os.listdir(data_root)]
         print("Preparing dataset...")
         for path in tqdm.tqdm(self.image_paths):
-            image = Image.open(path)
-            image = image.convert('RGB')
-            image = image.resize((self.width, self.height), PIL.Image.BICUBIC)
+            try:
+                image = Image.open(path).convert('RGB').resize((self.width, self.height), PIL.Image.BICUBIC)
+            except Exception:
+                continue
 
             filename = os.path.basename(path)
             filename_tokens = os.path.splitext(filename)[0]
@@ -52,7 +55,13 @@ class PersonalizedBase(Dataset):
             init_latent = model.get_first_stage_encoding(model.encode_first_stage(torchdata.unsqueeze(dim=0))).squeeze()
             init_latent = init_latent.to(devices.cpu)
 
-            self.dataset.append((init_latent, filename_tokens))
+            if include_cond:
+                text = self.create_text(filename_tokens)
+                cond = cond_model([text]).to(devices.cpu)
+            else:
+                cond = None
+
+            self.dataset.append((init_latent, filename_tokens, cond))
 
         self.length = len(self.dataset) * repeats
 
@@ -63,6 +72,12 @@ class PersonalizedBase(Dataset):
     def shuffle(self):
         self.indexes = self.initial_indexes[torch.randperm(self.initial_indexes.shape[0])]
 
+    def create_text(self, filename_tokens):
+        text = random.choice(self.lines)
+        text = text.replace("[name]", self.placeholder_token)
+        text = text.replace("[filewords]", ' '.join(filename_tokens))
+        return text
+
     def __len__(self):
         return self.length
 
@@ -71,10 +86,7 @@ class PersonalizedBase(Dataset):
             self.shuffle()
 
         index = self.indexes[i % len(self.indexes)]
-        x, filename_tokens = self.dataset[index]
-
-        text = random.choice(self.lines)
-        text = text.replace("[name]", self.placeholder_token)
-        text = text.replace("[filewords]", ' '.join(filename_tokens))
+        x, filename_tokens, cond = self.dataset[index]
 
-        return x, text
+        text = self.create_text(filename_tokens)
+        return x, text, cond

modules/textual_inversion/learn_schedule.py

+
+class LearnSchedule:
+    def __init__(self, learn_rate, max_steps, cur_step=0):
+        pairs = learn_rate.split(',')
+        self.rates = []
+        self.it = 0
+        self.maxit = 0
+        for i, pair in enumerate(pairs):
+            tmp = pair.split(':')
+            if len(tmp) == 2:
+                step = int(tmp[1])
+                if step > cur_step:
+                    self.rates.append((float(tmp[0]), min(step, max_steps)))
+                    self.maxit += 1
+                    if step > max_steps:
+                        return
+                elif step == -1:
+                    self.rates.append((float(tmp[0]), max_steps))
+                    self.maxit += 1
+                    return
+            else:
+                self.rates.append((float(tmp[0]), max_steps))
+                self.maxit += 1
+                return
+
+    def __iter__(self):
+        return self
+
+    def __next__(self):
+        if self.it < self.maxit:
+            self.it += 1
+            return self.rates[self.it - 1]
+        else:
+            raise StopIteration

modules/textual_inversion/preprocess.py

@@ -3,11 +3,14 @@ from PIL import Image, ImageOps
 import platform
 import sys
 import tqdm
+import time
 
 from modules import shared, images
+from modules.shared import opts, cmd_opts
+if cmd_opts.deepdanbooru:
+    import modules.deepbooru as deepbooru
 
-
-def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption):
+def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False):
     width = process_width
     height = process_height
     src = os.path.abspath(process_src)
@@ -25,10 +28,21 @@ def preprocess(process_src, process_dst, process_width, process_height, process_
     if process_caption:
         shared.interrogator.load()
 
+    if process_caption_deepbooru:
+        deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, opts.deepbooru_sort_alpha)
+
     def save_pic_with_caption(image, index):
         if process_caption:
             caption = "-" + shared.interrogator.generate_caption(image)
             caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
+        elif process_caption_deepbooru:
+            shared.deepbooru_process_return["value"] = -1
+            shared.deepbooru_process_queue.put(image)
+            while shared.deepbooru_process_return["value"] == -1:
+                time.sleep(0.2)
+            caption = "-" + shared.deepbooru_process_return["value"]
+            caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
+            shared.deepbooru_process_return["value"] = -1
         else:
             caption = filename
             caption = os.path.splitext(caption)[0]
@@ -46,7 +60,10 @@ def preprocess(process_src, process_dst, process_width, process_height, process_
     for index, imagefile in enumerate(tqdm.tqdm(files)):
         subindex = [0]
         filename = os.path.join(src, imagefile)
-        img = Image.open(filename).convert("RGB")
+        try:
+            img = Image.open(filename).convert("RGB")
+        except Exception:
+            continue
 
         if shared.state.interrupted:
             break
@@ -80,6 +97,10 @@ def preprocess(process_src, process_dst, process_width, process_height, process_
     if process_caption:
         shared.interrogator.send_blip_to_ram()
 
+    if process_caption_deepbooru:
+        deepbooru.release_process()
+
+
 def sanitize_caption(base_path, original_caption, suffix):
     operating_system = platform.system().lower()
     if (operating_system == "windows"):

modules/textual_inversion/textual_inversion.py

@@ -10,6 +10,7 @@ import datetime
 
 from modules import shared, devices, sd_hijack, processing, sd_models
 import modules.textual_inversion.dataset
+from modules.textual_inversion.learn_schedule import LearnSchedule
 
 
 class Embedding:
@@ -189,8 +190,6 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
     embedding = hijack.embedding_db.word_embeddings[embedding_name]
     embedding.vec.requires_grad = True
 
-    optimizer = torch.optim.AdamW([embedding.vec], lr=learn_rate)
-
     losses = torch.zeros((32,))
 
     last_saved_file = "<none>"
@@ -200,15 +199,24 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
     if ititial_step > steps:
         return embedding, filename
 
-    tr_img_len = len([os.path.join(data_root, file_path) for file_path in os.listdir(data_root)])
-    epoch_len = (tr_img_len * num_repeats) + tr_img_len
+    schedules = iter(LearnSchedule(learn_rate, steps, ititial_step))
+    (learn_rate, end_step) = next(schedules)
+    print(f'Training at rate of {learn_rate} until step {end_step}')
+
+    optimizer = torch.optim.AdamW([embedding.vec], lr=learn_rate)
 
     pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
-    for i, (x, text) in pbar:
+    for i, (x, text, _) in pbar:
         embedding.step = i + ititial_step
 
-        if embedding.step > steps:
-            break
+        if embedding.step > end_step:
+            try:
+                (learn_rate, end_step) = next(schedules)
+            except:
+                break
+            tqdm.tqdm.write(f'Training at rate of {learn_rate} until step {end_step}')
+            for pg in optimizer.param_groups:
+                pg['lr'] = learn_rate
 
         if shared.state.interrupted:
             break
@@ -226,10 +234,10 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, traini
             loss.backward()
             optimizer.step()
 
-        epoch_num = embedding.step // epoch_len
-        epoch_step = embedding.step - (epoch_num * epoch_len) + 1
+        epoch_num = embedding.step // len(ds)
+        epoch_step = embedding.step - (epoch_num * len(ds)) + 1
 
-        pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{epoch_len}]loss: {losses.mean():.7f}")
+        pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{len(ds)}]loss: {losses.mean():.7f}")
 
         if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0:
             last_saved_file = os.path.join(embedding_dir, f'{embedding_name}-{embedding.step}.pt')
@@ -278,4 +286,3 @@ Last saved image: {html.escape(last_saved_image)}<br/>
     embedding.save(filename)
 
     return embedding, filename
-

modules/textual_inversion/ui.py

@@ -22,6 +22,9 @@ def preprocess(*args):
 
 
 def train_embedding(*args):
+
+    assert not shared.cmd_opts.lowvram, 'Training models with lowvram not possible'
+
     try:
         sd_hijack.undo_optimizations()
 

requirements.txt

@@ -4,7 +4,7 @@ fairscale==0.4.4
 fonts
 font-roboto
 gfpgan
-gradio==3.4b3
+gradio==3.4.1
 invisible-watermark
 numpy
 omegaconf

requirements_versions.txt

@@ -2,7 +2,7 @@ transformers==4.19.2
 diffusers==0.3.0
 basicsr==1.4.2
 gfpgan==1.3.8
-gradio==3.4b3
+gradio==3.4.1
 numpy==1.23.3
 Pillow==9.2.0
 realesrgan==0.3.0

scripts/img2imgalt.py

@@ -129,8 +129,6 @@ class Script(scripts.Script):
         return [original_prompt, original_negative_prompt, cfg, st, randomness, sigma_adjustment]
 
     def run(self, p, original_prompt, original_negative_prompt, cfg, st, randomness, sigma_adjustment):
-        p.batch_size = 1
-        p.batch_count = 1
 
 
         def sample_extra(conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
@@ -154,7 +152,7 @@ class Script(scripts.Script):
                     rec_noise = find_noise_for_image(p, cond, uncond, cfg, st)
                 self.cache = Cached(rec_noise, cfg, st, lat, original_prompt, original_negative_prompt, sigma_adjustment)
 
-            rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], [p.seed + x + 1 for x in range(p.init_latent.shape[0])])
+            rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, seed_resize_from_h=p.seed_resize_from_h, seed_resize_from_w=p.seed_resize_from_w, p=p)
             
             combined_noise = ((1 - randomness) * rec_noise + randomness * rand_noise) / ((randomness**2 + (1-randomness)**2) ** 0.5)
             

scripts/xy_grid.py

@@ -77,14 +77,42 @@ def apply_sampler(p, x, xs):
     p.sampler_index = sampler_index
 
 
+def confirm_samplers(p, xs):
+    samplers_dict = build_samplers_dict(p)
+    for x in xs:
+        if x.lower() not in samplers_dict.keys():
+            raise RuntimeError(f"Unknown sampler: {x}")
+
+
 def apply_checkpoint(p, x, xs):
     info = modules.sd_models.get_closet_checkpoint_match(x)
-    assert info is not None, f'Checkpoint for {x} not found'
+    if info is None:
+        raise RuntimeError(f"Unknown checkpoint: {x}")
     modules.sd_models.reload_model_weights(shared.sd_model, info)
 
 
+def confirm_checkpoints(p, xs):
+    for x in xs:
+        if modules.sd_models.get_closet_checkpoint_match(x) is None:
+            raise RuntimeError(f"Unknown checkpoint: {x}")
+
+
 def apply_hypernetwork(p, x, xs):
-    hypernetwork.load_hypernetwork(x)
+    if x.lower() in ["", "none"]:
+        name = None
+    else:
+        name = hypernetwork.find_closest_hypernetwork_name(x)
+        if not name:
+            raise RuntimeError(f"Unknown hypernetwork: {x}")
+    hypernetwork.load_hypernetwork(name)
+
+
+def confirm_hypernetworks(p, xs):
+    for x in xs:
+        if x.lower() in ["", "none"]:
+            continue
+        if not hypernetwork.find_closest_hypernetwork_name(x):
+            raise RuntimeError(f"Unknown hypernetwork: {x}")
 
 
 def apply_clip_skip(p, x, xs):
@@ -121,29 +149,29 @@ def str_permutations(x):
     return x
 
 
-AxisOption = namedtuple("AxisOption", ["label", "type", "apply", "format_value"])
-AxisOptionImg2Img = namedtuple("AxisOptionImg2Img", ["label", "type", "apply", "format_value"])
+AxisOption = namedtuple("AxisOption", ["label", "type", "apply", "format_value", "confirm"])
+AxisOptionImg2Img = namedtuple("AxisOptionImg2Img", ["label", "type", "apply", "format_value", "confirm"])
 
 
 axis_options = [
-    AxisOption("Nothing", str, do_nothing, format_nothing),
-    AxisOption("Seed", int, apply_field("seed"), format_value_add_label),
-    AxisOption("Var. seed", int, apply_field("subseed"), format_value_add_label),
-    AxisOption("Var. strength", float, apply_field("subseed_strength"), format_value_add_label),
-    AxisOption("Steps", int, apply_field("steps"), format_value_add_label),
-    AxisOption("CFG Scale", float, apply_field("cfg_scale"), format_value_add_label),
-    AxisOption("Prompt S/R", str, apply_prompt, format_value),
-    AxisOption("Prompt order", str_permutations, apply_order, format_value_join_list),
-    AxisOption("Sampler", str, apply_sampler, format_value),
-    AxisOption("Checkpoint name", str, apply_checkpoint, format_value),
-    AxisOption("Hypernetwork", str, apply_hypernetwork, format_value),
-    AxisOption("Sigma Churn", float, apply_field("s_churn"), format_value_add_label),
-    AxisOption("Sigma min", float, apply_field("s_tmin"), format_value_add_label),
-    AxisOption("Sigma max", float, apply_field("s_tmax"), format_value_add_label),
-    AxisOption("Sigma noise", float, apply_field("s_noise"), format_value_add_label),
-    AxisOption("Eta", float, apply_field("eta"), format_value_add_label),
-    AxisOption("Clip skip", int, apply_clip_skip, format_value_add_label),
-    AxisOptionImg2Img("Denoising", float, apply_field("denoising_strength"), format_value_add_label),  # as it is now all AxisOptionImg2Img items must go after AxisOption ones
+    AxisOption("Nothing", str, do_nothing, format_nothing, None),
+    AxisOption("Seed", int, apply_field("seed"), format_value_add_label, None),
+    AxisOption("Var. seed", int, apply_field("subseed"), format_value_add_label, None),
+    AxisOption("Var. strength", float, apply_field("subseed_strength"), format_value_add_label, None),
+    AxisOption("Steps", int, apply_field("steps"), format_value_add_label, None),
+    AxisOption("CFG Scale", float, apply_field("cfg_scale"), format_value_add_label, None),
+    AxisOption("Prompt S/R", str, apply_prompt, format_value, None),
+    AxisOption("Prompt order", str_permutations, apply_order, format_value_join_list, None),
+    AxisOption("Sampler", str, apply_sampler, format_value, confirm_samplers),
+    AxisOption("Checkpoint name", str, apply_checkpoint, format_value, confirm_checkpoints),
+    AxisOption("Hypernetwork", str, apply_hypernetwork, format_value, confirm_hypernetworks),
+    AxisOption("Sigma Churn", float, apply_field("s_churn"), format_value_add_label, None),
+    AxisOption("Sigma min", float, apply_field("s_tmin"), format_value_add_label, None),
+    AxisOption("Sigma max", float, apply_field("s_tmax"), format_value_add_label, None),
+    AxisOption("Sigma noise", float, apply_field("s_noise"), format_value_add_label, None),
+    AxisOption("Eta", float, apply_field("eta"), format_value_add_label, None),
+    AxisOption("Clip skip", int, apply_clip_skip, format_value_add_label, None),
+    AxisOptionImg2Img("Denoising", float, apply_field("denoising_strength"), format_value_add_label, None),  # as it is now all AxisOptionImg2Img items must go after AxisOption ones
 ]
 
 
@@ -197,7 +225,7 @@ class Script(scripts.Script):
             x_values = gr.Textbox(label="X values", visible=False, lines=1)
 
         with gr.Row():
-            y_type = gr.Dropdown(label="Y type", choices=[x.label for x in current_axis_options], value=current_axis_options[4].label, visible=False, type="index", elem_id="y_type")
+            y_type = gr.Dropdown(label="Y type", choices=[x.label for x in current_axis_options], value=current_axis_options[0].label, visible=False, type="index", elem_id="y_type")
             y_values = gr.Textbox(label="Y values", visible=False, lines=1)
         
         draw_legend = gr.Checkbox(label='Draw legend', value=True)
@@ -269,17 +297,10 @@ class Script(scripts.Script):
                 valslist = list(permutations(valslist))
 
             valslist = [opt.type(x) for x in valslist]
-            
+
             # Confirm options are valid before starting
-            if opt.label == "Sampler":
-                samplers_dict = build_samplers_dict(p)
-                for sampler_val in valslist:
-                    if sampler_val.lower() not in samplers_dict.keys():
-                        raise RuntimeError(f"Unknown sampler: {sampler_val}")
-            elif opt.label == "Checkpoint name":
-                for ckpt_val in valslist:
-                    if modules.sd_models.get_closet_checkpoint_match(ckpt_val) is None:
-                        raise RuntimeError(f"Checkpoint for {ckpt_val} not found")
+            if opt.confirm:
+                opt.confirm(p, valslist)
 
             return valslist
 

style.css

@@ -240,6 +240,7 @@ fieldset span.text-gray-500, .gr-block.gr-box span.text-gray-500,  label.block s
 #settings fieldset span.text-gray-500, #settings .gr-block.gr-box span.text-gray-500, #settings label.block span{
     position: relative;
     border: none;
+    margin-right: 8em;
 }
 
 .gr-panel div.flex-col div.justify-between label span{
@@ -494,4 +495,14 @@ canvas[key="mask"] {
     filter: invert();
     mix-blend-mode: multiply;
     pointer-events: none;
+}
+
+
+/* gradio 3.4.1 stuff for editable scrollbar values */
+.gr-box > div > div > input.gr-text-input{
+    position: absolute;
+    right: 0.5em;
+    top: -0.6em;
+    z-index: 200;
+    width: 8em;
 }
\ No newline at end of file

webui.py

@@ -31,12 +31,7 @@ from modules.paths import script_path
 from modules.shared import cmd_opts
 import modules.hypernetworks.hypernetwork
 
-modelloader.cleanup_models()
-modules.sd_models.setup_model()
-codeformer.setup_model(cmd_opts.codeformer_models_path)
-gfpgan.setup_model(cmd_opts.gfpgan_models_path)
-shared.face_restorers.append(modules.face_restoration.FaceRestoration())
-modelloader.load_upscalers()
+
 queue_lock = threading.Lock()
 
 
@@ -78,15 +73,24 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
     return modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs)
 
 
-modules.scripts.load_scripts(os.path.join(script_path, "scripts"))
+def initialize():
+    modelloader.cleanup_models()
+    modules.sd_models.setup_model()
+    codeformer.setup_model(cmd_opts.codeformer_models_path)
+    gfpgan.setup_model(cmd_opts.gfpgan_models_path)
+    shared.face_restorers.append(modules.face_restoration.FaceRestoration())
+    modelloader.load_upscalers()
 
-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)))
+    modules.scripts.load_scripts(os.path.join(script_path, "scripts"))
 
-shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetworks.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
+    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.hypernetworks.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
 
 
 def webui():
+    initialize()
+    
     # make the program just exit at ctrl+c without waiting for anything
     def sigint_handler(sig, frame):
         print(f'Interrupted with signal {sig} in {frame}')
@@ -98,7 +102,7 @@ def webui():
 
         demo = modules.ui.create_ui(wrap_gradio_gpu_call=wrap_gradio_gpu_call)
         
-        app,local_url,share_url = demo.launch(
+        app, local_url, share_url = demo.launch(
             share=cmd_opts.share,
             server_name="0.0.0.0" if cmd_opts.listen else None,
             server_port=cmd_opts.port,
@@ -124,9 +128,10 @@ def webui():
         modules.scripts.reload_scripts(os.path.join(script_path, "scripts"))
         print('Reloading modules: modules.ui')
         importlib.reload(modules.ui)
+        print('Refreshing Model List')
+        modules.sd_models.list_models()
         print('Restarting Gradio')
 
 
-
 if __name__ == "__main__":
     webui()