Merge branch 'master' into feature/scale_to

.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: ''
 
 ---

.github/PULL_REQUEST_TEMPLATE/pull_request_template.md

+# Please read the [contributing wiki page](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing) before submitting a pull request!
+
+If you have a large change, pay special attention to this paragraph:
+
+> Before making changes, if you think that your feature will result in more than 100 lines changing, find me and talk to me about the feature you are proposing. It pains me to reject the hard work someone else did, but I won't add everything to the repo, and it's better if the rejection happens before you have to waste time working on the feature.
+
+Otherwise, after making sure you're following the rules described in wiki page, remove this section and continue on.
+
+**Describe what this pull request is trying to achieve.**
+
+A clear and concise description of what you're trying to accomplish with this, so your intent doesn't have to be extracted from your code.
+
+**Additional notes and description of your changes**
+
+More technical discussion about your changes go here, plus anything that a maintainer might have to specifically take a look at, or be wary of.
+
+**Environment this was tested in**
+
+List the environment you have developed / tested this on. As per the contributing page, changes should be able to work on Windows out of the box.
+ - OS: [e.g. Windows, Linux]
+ - Browser [e.g. chrome, safari]
+ - Graphics card [e.g. NVIDIA RTX 2080 8GB, AMD RX 6600 8GB]
+
+**Screenshots or videos of your changes**
+
+If applicable, screenshots or a video showing off your changes. If it edits an existing UI, it should ideally contain a comparison of what used to be there, before your changes were made.
+
+This is **required** for anything that touches the user interface.
\ No newline at end of file

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)

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/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')
@@ -123,48 +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
-generateOnRepeatId = appendContextMenuOption('#txt2img_generate','Generate forever',function(){
-  let genbutton = gradioApp().querySelector('#txt2img_generate');
-  let interruptbutton = gradioApp().querySelector('#txt2img_interrupt');
-  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)}
-)
-
-cancelGenerateForever = function(){ 
-  clearInterval(window.generateOnRepeatInterval) 
-  let interruptbutton = gradioApp().querySelector('#txt2img_interrupt');
-  if(interruptbutton.offsetParent){
-      interruptbutton.click();
+    clearInterval(window.generateOnRepeatInterval)
+    window.generateOnRepeatInterval = setInterval(function(){
+      if(!interruptbutton.offsetParent){
+        genbutton.click();
+      }
+    },
+    500)
   }
-}
 
-appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)
-appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever)
+  appendContextMenuOption('#txt2img_generate','Generate forever',function(){
+    generateOnRepeat('#txt2img_generate','#txt2img_interrupt');
+  })
+  appendContextMenuOption('#img2img_generate','Generate forever',function(){
+    generateOnRepeat('#img2img_generate','#img2img_interrupt');
+  })
 
-
-appendContextMenuOption('#roll','Roll three',
-  function(){ 
-    let rollbutton = gradioApp().querySelector('#roll');
-    setTimeout(function(){rollbutton.click()},100)
-    setTimeout(function(){rollbutton.click()},200)
-    setTimeout(function(){rollbutton.click()},300)
+  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(){

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

@@ -79,6 +79,8 @@ 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.",
+    "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.",
 }
 
 

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()
@@ -127,13 +128,16 @@ 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")
 
     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)

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/devices.py

@@ -36,6 +36,7 @@ errors.run(enable_tf32, "Enabling TF32")
 
 device = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = get_optimal_device()
 dtype = torch.float16
+dtype_vae = torch.float16
 
 def randn(seed, shape):
     # Pytorch currently doesn't handle setting randomness correctly when the metal backend is used.
@@ -59,9 +60,12 @@ def randn_without_seed(shape):
     return torch.randn(shape, device=device)
 
 
-def autocast():
+def autocast(disable=False):
     from modules import shared
 
+    if disable:
+        return contextlib.nullcontext()
+
     if dtype == torch.float32 or shared.cmd_opts.precision == "full":
         return contextlib.nullcontext()
 

modules/hypernetwork.py

-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 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)
-
-    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)

modules/hypernetworks/ui.py

+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, devices
+from modules.hypernetworks import hypernetwork
+
+
+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, enable_sizes=[int(x) for x in enable_sizes])
+    hypernet.save(fn)
+
+    shared.reload_hypernetworks()
+
+    return gr.Dropdown.update(choices=sorted([x for x in shared.hypernetworks.keys()])), f"Created: {fn}", ""
+
+
+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()
+
+        hypernetwork, filename = modules.hypernetworks.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.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/ngrok.py

+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.')

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)))
 
@@ -259,6 +262,13 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
     return x
 
 
+def decode_first_stage(model, x):
+    with devices.autocast(disable=x.dtype == devices.dtype_vae):
+        x = model.decode_first_stage(x)
+
+    return x
+
+
 def get_fixed_seed(seed):
     if seed is None or seed == '' or seed == -1:
         return int(random.randrange(4294967294))
@@ -294,6 +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)
@@ -398,9 +409,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
                 # use the image collected previously in sampler loop
                 samples_ddim = shared.state.current_latent
 
-            samples_ddim = samples_ddim.to(devices.dtype)
-
-            x_samples_ddim = p.sd_model.decode_first_stage(samples_ddim)
+            samples_ddim = samples_ddim.to(devices.dtype_vae)
+            x_samples_ddim = decode_first_stage(p.sd_model, samples_ddim)
             x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
 
             del samples_ddim
@@ -533,7 +543,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         if self.scale_latent:
             samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
         else:
-            decoded_samples = self.sd_model.decode_first_stage(samples)
+            decoded_samples = decode_first_stage(self.sd_model, samples)
 
             if opts.upscaler_for_img2img is None or opts.upscaler_for_img2img == "None":
                 decoded_samples = torch.nn.functional.interpolate(decoded_samples, size=(self.height, self.width), mode="bilinear")

modules/safe.py

@@ -10,6 +10,11 @@ import torch
 import numpy
 import _codecs
 import zipfile
+import re
+
+
+# PyTorch 1.13 and later have _TypedStorage renamed to TypedStorage
+TypedStorage = torch.storage.TypedStorage if hasattr(torch.storage, 'TypedStorage') else torch.storage._TypedStorage
 
 
 def encode(*args):
@@ -20,7 +25,7 @@ def encode(*args):
 class RestrictedUnpickler(pickle.Unpickler):
     def persistent_load(self, saved_id):
         assert saved_id[0] == 'storage'
-        return torch.storage._TypedStorage()
+        return TypedStorage()
 
     def find_class(self, module, name):
         if module == 'collections' and name == 'OrderedDict':
@@ -50,11 +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_optimizations.py

 import math
 import sys
 import traceback
+import importlib
 
 import torch
 from torch import einsum
@@ -9,12 +10,12 @@ from ldm.util import default
 from einops import rearrange
 
 from modules import shared
+from modules.hypernetworks import hypernetwork
+
 
 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)
@@ -28,16 +29,10 @@ 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
@@ -61,22 +56,16 @@ 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
 
@@ -128,18 +117,111 @@ 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)
     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)

modules/sd_models.py

@@ -149,8 +149,13 @@ def load_model_weights(model, checkpoint_info):
         model.half()
 
     devices.dtype = torch.float32 if shared.cmd_opts.no_half else torch.float16
+    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 not os.path.exists(vae_file) and shared.cmd_opts.vae_path is not None:
+        vae_file = shared.cmd_opts.vae_path
+
     if os.path.exists(vae_file):
         print(f"Loading VAE weights from: {vae_file}")
         vae_ckpt = torch.load(vae_file, map_location="cpu")
@@ -158,6 +163,8 @@ def load_model_weights(model, checkpoint_info):
 
         model.first_stage_model.load_state_dict(vae_dict)
 
+    model.first_stage_model.to(devices.dtype_vae)
+
     model.sd_model_hash = sd_model_hash
     model.sd_model_checkpoint = checkpoint_file
     model.sd_checkpoint_info = checkpoint_info

modules/sd_samplers.py

@@ -7,7 +7,7 @@ import inspect
 import k_diffusion.sampling
 import ldm.models.diffusion.ddim
 import ldm.models.diffusion.plms
-from modules import prompt_parser
+from modules import prompt_parser, devices, processing
 
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
@@ -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]
@@ -83,7 +83,7 @@ def setup_img2img_steps(p, steps=None):
 
 
 def sample_to_image(samples):
-    x_sample = shared.sd_model.decode_first_stage(samples[0:1].type(shared.sd_model.dtype))[0]
+    x_sample = processing.decode_first_stage(shared.sd_model, samples[0:1])[0]
     x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)
     x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
     x_sample = x_sample.astype(np.uint8)
@@ -365,16 +365,26 @@ 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:]
+        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 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]
+        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

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

modules/textual_inversion/dataset.py

@@ -8,18 +8,17 @@ 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, size=None, repeats=100, flip_p=0.5, placeholder_token="*", width=512, height=512, 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
 
-        self.size = size
         self.width = width
         self.height = height
         self.flip = transforms.RandomHorizontalFlip(p=flip_p)
@@ -33,12 +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]
@@ -53,7 +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
 
@@ -64,6 +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
 
@@ -72,10 +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

@@ -3,12 +3,16 @@ 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_flip, process_split, process_caption):
-    size = 512
+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)
     dst = os.path.abspath(process_dst)
 
@@ -24,10 +28,21 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
     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]
@@ -45,7 +60,10 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
     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
@@ -55,23 +73,23 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
         is_wide = ratio < 1 / 1.35
 
         if process_split and is_tall:
-            img = img.resize((size, size * img.height // img.width))
+            img = img.resize((width, height * img.height // img.width))
 
-            top = img.crop((0, 0, size, size))
+            top = img.crop((0, 0, width, height))
             save_pic(top, index)
 
-            bot = img.crop((0, img.height - size, size, img.height))
+            bot = img.crop((0, img.height - height, width, img.height))
             save_pic(bot, index)
         elif process_split and is_wide:
-            img = img.resize((size * img.width // img.height, size))
+            img = img.resize((width * img.width // img.height, height))
 
-            left = img.crop((0, 0, size, size))
+            left = img.crop((0, 0, width, height))
             save_pic(left, index)
 
-            right = img.crop((img.width - size, 0, img.width, size))
+            right = img.crop((img.width - width, 0, img.width, height))
             save_pic(right, index)
         else:
-            img = images.resize_image(1, img, size, size)
+            img = images.resize_image(1, img, width, height)
             save_pic(img, index)
 
         shared.state.nextjob()
@@ -79,6 +97,10 @@ def preprocess(process_src, process_dst, process_flip, process_split, process_ca
     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:
@@ -156,7 +157,7 @@ def create_embedding(name, num_vectors_per_token, init_text='*'):
     return fn
 
 
-def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps, 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..."
@@ -182,15 +183,13 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
 
     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=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
+        ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=num_repeats, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file)
 
     hijack = sd_hijack.model_hijack
 
     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>"
@@ -200,12 +199,24 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
     if ititial_step > steps:
         return embedding, 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([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
@@ -223,7 +234,10 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
             loss.backward()
             optimizer.step()
 
-        pbar.set_description(f"loss: {losses.mean():.7f}")
+        epoch_num = embedding.step // len(ds)
+        epoch_step = embedding.step - (epoch_num * len(ds)) + 1
+
+        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')
@@ -232,10 +246,14 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
         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,
                 do_not_save_grid=True,
                 do_not_save_samples=True,
             )
@@ -246,7 +264,7 @@ def train_embedding(embedding_name, learn_rate, data_root, log_directory, steps,
             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
 
@@ -268,4 +286,3 @@ Last saved image: {html.escape(last_saved_image)}<br/>
     embedding.save(filename)
 
     return embedding, filename
-

modules/textual_inversion/ui.py

@@ -23,6 +23,8 @@ 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
@@ -23,4 +23,3 @@ resize-right
 torchdiffeq
 kornia
 lark
-functorch

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
@@ -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

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
@@ -40,6 +44,25 @@ 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) {
+        button = get_uiCurrentTabContent().querySelector('button[id$=_generate]');
+        if (button) {
+            button.click();
+        }
+        e.preventDefault();
+    }
+})
+
 /**
  * checks that a UI element is not in another hidden element or tab content
  */

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/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

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.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
@@ -27,6 +28,9 @@ def apply_field(field):
 
 
 def apply_prompt(p, x, xs):
+    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)
 
@@ -193,7 +197,7 @@ 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)
@@ -205,7 +209,10 @@ 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):

style.css

+.container {
+    max-width: 100%;
+}
+
+#txt2img_token_counter {
+    height: 0px;
+}
+
+#img2img_token_counter {
+    height: 0px;
+}
+
+#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%;
+    cursor: default;	
+}
+
 .output-html p {margin: 0 0.5em;}
 
 .row > *,
@@ -215,6 +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{
@@ -463,3 +489,20 @@ input[type="range"]{
     max-width: 32em;
     padding: 0;
 }
+
+canvas[key="mask"] {
+    z-index: 12 !important;
+    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;
+}

textual_inversion_templates/hypernetwork.txt

+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]

textual_inversion_templates/none.txt

+picture

webui.py

@@ -29,13 +29,9 @@ from modules import devices
 from modules import modelloader
 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()
 
 
@@ -77,16 +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"))
 
-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.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,
@@ -108,7 +112,7 @@ 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)
@@ -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()