reshuffle the code a bit in launcher to keep functions in one place for #2069

Fixes #1049

README.md

@@ -16,7 +16,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - Attention, specify parts of text that the model should pay more attention to
     - a man in a ((tuxedo)) - will pay more attention to tuxedo
     - a man in a (tuxedo:1.21) - alternative syntax
-    - select text and press ctrl+up or ctrl+down to aduotmatically adjust attention to selected text
+    - select text and press ctrl+up or ctrl+down to automatically adjust attention to selected text (code contributed by anonymous user)
 - Loopback, run img2img processing multiple times
 - X/Y plot, a way to draw a 2 dimensional plot of images with different parameters
 - Textual Inversion
@@ -34,7 +34,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - Sampling method selection
 - Interrupt processing at any time
 - 4GB video card support (also reports of 2GB working)
-- Correct seeds for batches 
+- Correct seeds for batches
 - Prompt length validation
      - get length of prompt in tokens as you type
      - get a warning after generation if some text was truncated
@@ -65,6 +65,8 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once
      - separate prompts using uppercase `AND`
      - 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)
 
 ## 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.
@@ -122,4 +124,5 @@ The documentation was moved from this README over to the project's [wiki](https:
 - 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
 - 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)

javascript/contextMenus.js

@@ -0,0 +1,172 @@
+
+contextMenuInit = function(){
+  let eventListenerApplied=false;
+  let menuSpecs = new Map();
+
+  const uid = function(){
+    return Date.now().toString(36) + Math.random().toString(36).substr(2);
+  }
+
+  function showContextMenu(event,element,menuEntries){
+    let posx = event.clientX + document.body.scrollLeft + document.documentElement.scrollLeft;
+    let posy = event.clientY + document.body.scrollTop + document.documentElement.scrollTop; 
+
+    let oldMenu = gradioApp().querySelector('#context-menu')
+    if(oldMenu){
+      oldMenu.remove()
+    }
+
+    let tabButton = gradioApp().querySelector('button')
+    let baseStyle = window.getComputedStyle(tabButton)
+
+    const contextMenu = document.createElement('nav')
+    contextMenu.id = "context-menu"
+    contextMenu.style.background = baseStyle.background
+    contextMenu.style.color = baseStyle.color
+    contextMenu.style.fontFamily = baseStyle.fontFamily
+    contextMenu.style.top = posy+'px'
+    contextMenu.style.left = posx+'px'
+
+
+
+    const contextMenuList = document.createElement('ul')
+    contextMenuList.className = 'context-menu-items';
+    contextMenu.append(contextMenuList);
+
+    menuEntries.forEach(function(entry){
+      let contextMenuEntry = document.createElement('a')
+      contextMenuEntry.innerHTML = entry['name']
+      contextMenuEntry.addEventListener("click", function(e) {
+        entry['func']();
+      })
+      contextMenuList.append(contextMenuEntry);
+
+    })
+
+    gradioApp().getRootNode().appendChild(contextMenu)
+
+    let menuWidth = contextMenu.offsetWidth + 4;
+    let menuHeight = contextMenu.offsetHeight + 4;
+
+    let windowWidth = window.innerWidth;
+    let windowHeight = window.innerHeight;
+
+    if ( (windowWidth - posx) < menuWidth ) {
+      contextMenu.style.left = windowWidth - menuWidth + "px";
+    }
+
+    if ( (windowHeight - posy) < menuHeight ) {
+      contextMenu.style.top = windowHeight - menuHeight + "px";
+    }
+
+  }
+
+  function appendContextMenuOption(targetEmementSelector,entryName,entryFunction){
+    
+    currentItems = menuSpecs.get(targetEmementSelector)
+    
+    if(!currentItems){
+      currentItems = []
+      menuSpecs.set(targetEmementSelector,currentItems);
+    }
+    let newItem = {'id':targetEmementSelector+'_'+uid(), 
+                   'name':entryName,
+                   'func':entryFunction,
+                   'isNew':true}
+
+    currentItems.push(newItem)
+    return newItem['id']
+  }
+
+  function removeContextMenuOption(uid){
+    menuSpecs.forEach(function(v,k) {
+      let index = -1
+      v.forEach(function(e,ei){if(e['id']==uid){index=ei}})
+      if(index>=0){
+        v.splice(index, 1);
+      }
+    })
+  }
+
+  function addContextMenuEventListener(){
+    if(eventListenerApplied){
+      return;
+    }
+    gradioApp().addEventListener("click", function(e) {
+      let source = e.composedPath()[0]
+      if(source.id && source.indexOf('check_progress')>-1){
+        return
+      }
+      
+      let oldMenu = gradioApp().querySelector('#context-menu')
+      if(oldMenu){
+        oldMenu.remove()
+      }
+    });
+    gradioApp().addEventListener("contextmenu", function(e) {
+      let oldMenu = gradioApp().querySelector('#context-menu')
+      if(oldMenu){
+        oldMenu.remove()
+      }
+      menuSpecs.forEach(function(v,k) {
+        if(e.composedPath()[0].matches(k)){
+          showContextMenu(e,e.composedPath()[0],v)
+          e.preventDefault()
+          return
+        }
+      })
+    });
+    eventListenerApplied=true
+  
+  }
+
+  return [appendContextMenuOption, removeContextMenuOption, addContextMenuEventListener]
+}
+
+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(){
+    if(!interruptbutton.offsetParent){
+      genbutton.click();
+    }
+  },
+  500)}
+)
+
+cancelGenerateForever = function(){ 
+  clearInterval(window.generateOnRepeatInterval) 
+  let interruptbutton = gradioApp().querySelector('#txt2img_interrupt');
+  if(interruptbutton.offsetParent){
+      interruptbutton.click();
+  }
+}
+
+appendContextMenuOption('#txt2img_interrupt','Cancel generate forever',cancelGenerateForever)
+appendContextMenuOption('#txt2img_generate', 'Cancel generate forever',cancelGenerateForever)
+
+
+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)
+  }
+)
+//End example Context Menu Items
+
+onUiUpdate(function(){
+  addContextMenuEventListener()
+});

javascript/edit-attention.js

@@ -1,5 +1,5 @@
 addEventListener('keydown', (event) => {
-	let target = event.originalTarget;
+	let target = event.originalTarget || event.composedPath()[0];
 	if (!target.hasAttribute("placeholder")) return;
 	if (!target.placeholder.toLowerCase().includes("prompt")) return;
 

javascript/hints.js

@@ -35,6 +35,7 @@ titles = {
     "Denoising strength": "Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.",
     "Denoising strength change factor": "In loopback mode, on each loop the denoising strength is multiplied by this value. <1 means decreasing variety so your sequence will converge on a fixed picture. >1 means increasing variety so your sequence will become more and more chaotic.",
 
+    "Skip": "Stop processing current image and continue processing.",
     "Interrupt": "Stop processing images and return any results accumulated so far.",
     "Save": "Write image to a directory (default - log/images) and generation parameters into csv file.",
 

javascript/imageviewer.js

@@ -86,13 +86,16 @@ function showGalleryImage(){
         
         if(fullImg_preview != null){
             fullImg_preview.forEach(function function_name(e) {
+                if (e.dataset.modded)
+                    return;
+                e.dataset.modded = true;
                 if(e && e.parentElement.tagName == 'DIV'){
 
                     e.style.cursor='pointer'
 
                     e.addEventListener('click', function (evt) {
                         if(!opts.js_modal_lightbox) return;
-                        modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initialy_zoomed)
+                        modalZoomSet(gradioApp().getElementById('modalImage'), opts.js_modal_lightbox_initially_zoomed)
                         showModal(evt)
                     },true);
                 }

javascript/progressbar.js

@@ -1,8 +1,9 @@
 // code related to showing and updating progressbar shown as the image is being made
 global_progressbars = {}
 
-function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_interrupt, id_preview, id_gallery){
+function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip, id_interrupt, id_preview, id_gallery){
     var progressbar = gradioApp().getElementById(id_progressbar)
+    var skip = id_skip ? gradioApp().getElementById(id_skip) : null
     var interrupt = gradioApp().getElementById(id_interrupt)
     
     if(opts.show_progress_in_title && progressbar && progressbar.offsetParent){
@@ -32,30 +33,37 @@ function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_inte
 
                 var progressDiv = gradioApp().querySelectorAll('#' + id_progressbar_span).length > 0;
                 if(!progressDiv){
+                    if (skip) {
+                        skip.style.display = "none"
+                    }
                     interrupt.style.display = "none"
                 }
             }
 
-            window.setTimeout(function(){ requestMoreProgress(id_part, id_progressbar_span, id_interrupt) }, 500)
+            window.setTimeout(function() { requestMoreProgress(id_part, id_progressbar_span, id_skip, id_interrupt) }, 500)
         });
         mutationObserver.observe( progressbar, { childList:true, subtree:true })
 	}
 }
 
 onUiUpdate(function(){
-    check_progressbar('txt2img', 'txt2img_progressbar', 'txt2img_progress_span', 'txt2img_interrupt', 'txt2img_preview', 'txt2img_gallery')
-    check_progressbar('img2img', 'img2img_progressbar', 'img2img_progress_span', 'img2img_interrupt', 'img2img_preview', 'img2img_gallery')
-    check_progressbar('ti', 'ti_progressbar', 'ti_progress_span', 'ti_interrupt', 'ti_preview', 'ti_gallery')
+    check_progressbar('txt2img', 'txt2img_progressbar', 'txt2img_progress_span', 'txt2img_skip', 'txt2img_interrupt', 'txt2img_preview', 'txt2img_gallery')
+    check_progressbar('img2img', 'img2img_progressbar', 'img2img_progress_span', 'img2img_skip', 'img2img_interrupt', 'img2img_preview', 'img2img_gallery')
+    check_progressbar('ti', 'ti_progressbar', 'ti_progress_span', '', 'ti_interrupt', 'ti_preview', 'ti_gallery')
 })
 
-function requestMoreProgress(id_part, id_progressbar_span, id_interrupt){
+function requestMoreProgress(id_part, id_progressbar_span, id_skip, id_interrupt){
     btn = gradioApp().getElementById(id_part+"_check_progress");
     if(btn==null) return;
 
     btn.click();
     var progressDiv = gradioApp().querySelectorAll('#' + id_progressbar_span).length > 0;
+    var skip = id_skip ? gradioApp().getElementById(id_skip) : null
     var interrupt = gradioApp().getElementById(id_interrupt)
     if(progressDiv && interrupt){
+        if (skip) {
+            skip.style.display = "block"
+        }
         interrupt.style.display = "block"
     }
 }

launch.py

@@ -4,39 +4,17 @@ import os
 import sys
 import importlib.util
 import shlex
+import platform
 
 dir_repos = "repositories"
-dir_tmp = "tmp"
-
 python = sys.executable
 git = os.environ.get('GIT', "git")
-torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113")
-requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
-commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
-
-gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379")
-clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1")
-
-stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc")
-taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
-k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "f4e99857772fc3a126ba886aadf795a332774878")
-codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
-blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
-
-args = shlex.split(commandline_args)
 
 
 def extract_arg(args, name):
     return [x for x in args if x != name], name in args
 
 
-args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test')
-
-
-def repo_dir(name):
-    return os.path.join(dir_repos, name)
-
-
 def run(command, desc=None, errdesc=None):
     if desc is not None:
         print(desc)
@@ -56,23 +34,11 @@ stderr: {result.stderr.decode(encoding="utf8", errors="ignore") if len(result.st
     return result.stdout.decode(encoding="utf8", errors="ignore")
 
 
-def run_python(code, desc=None, errdesc=None):
-    return run(f'"{python}" -c "{code}"', desc, errdesc)
-
-
-def run_pip(args, desc=None):
-    return run(f'"{python}" -m pip {args} --prefer-binary', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}")
-
-
 def check_run(command):
     result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
     return result.returncode == 0
 
 
-def check_run_python(code):
-    return check_run(f'"{python}" -c "{code}"')
-
-
 def is_installed(package):
     try:
         spec = importlib.util.find_spec(package)
@@ -82,6 +48,22 @@ def is_installed(package):
     return spec is not None
 
 
+def repo_dir(name):
+    return os.path.join(dir_repos, name)
+
+
+def run_python(code, desc=None, errdesc=None):
+    return run(f'"{python}" -c "{code}"', desc, errdesc)
+
+
+def run_pip(args, desc=None):
+    return run(f'"{python}" -m pip {args} --prefer-binary', desc=f"Installing {desc}", errdesc=f"Couldn't install {desc}")
+
+
+def check_run_python(code):
+    return check_run(f'"{python}" -c "{code}"')
+
+
 def git_clone(url, dir, name, commithash=None):
     # TODO clone into temporary dir and move if successful
 
@@ -103,50 +85,81 @@ def git_clone(url, dir, name, commithash=None):
         run(f'"{git}" -C {dir} checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
 
 
-try:
-    commit = run(f"{git} rev-parse HEAD").strip()
-except Exception:
-    commit = "<none>"
+def prepare_enviroment():
+    torch_command = os.environ.get('TORCH_COMMAND', "pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113")
+    requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
+    commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
 
-print(f"Python {sys.version}")
-print(f"Commit hash: {commit}")
+    gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379")
+    clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1")
 
+    stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc")
+    taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
+    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "f4e99857772fc3a126ba886aadf795a332774878")
+    codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
+    blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
 
-if not is_installed("torch") or not is_installed("torchvision"):
-    run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch")
+    args = shlex.split(commandline_args)
 
-if not skip_torch_cuda_test:
-    run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
+    args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test')
+    xformers = '--xformers' in args
+    deepdanbooru = '--deepdanbooru' in args
 
-if not is_installed("gfpgan"):
-    run_pip(f"install {gfpgan_package}", "gfpgan")
+    try:
+        commit = run(f"{git} rev-parse HEAD").strip()
+    except Exception:
+        commit = "<none>"
 
-if not is_installed("clip"):
-    run_pip(f"install {clip_package}", "clip")
+    print(f"Python {sys.version}")
+    print(f"Commit hash: {commit}")
 
-os.makedirs(dir_repos, exist_ok=True)
+    if not is_installed("torch") or not is_installed("torchvision"):
+        run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch")
 
-git_clone("https://github.com/CompVis/stable-diffusion.git", repo_dir('stable-diffusion'), "Stable Diffusion", stable_diffusion_commit_hash)
-git_clone("https://github.com/CompVis/taming-transformers.git", repo_dir('taming-transformers'), "Taming Transformers", taming_transformers_commit_hash)
-git_clone("https://github.com/crowsonkb/k-diffusion.git", repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
-git_clone("https://github.com/sczhou/CodeFormer.git", repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
-git_clone("https://github.com/salesforce/BLIP.git", repo_dir('BLIP'), "BLIP", blip_commit_hash)
+    if not skip_torch_cuda_test:
+        run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
 
-if not is_installed("lpips"):
-    run_pip(f"install -r {os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}", "requirements for CodeFormer")
+    if not is_installed("gfpgan"):
+        run_pip(f"install {gfpgan_package}", "gfpgan")
 
-run_pip(f"install -r {requirements_file}", "requirements for Web UI")
+    if not is_installed("clip"):
+        run_pip(f"install {clip_package}", "clip")
 
-sys.argv += args
+    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")
+        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")
+
+    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)
+    git_clone("https://github.com/CompVis/taming-transformers.git", repo_dir('taming-transformers'), "Taming Transformers", taming_transformers_commit_hash)
+    git_clone("https://github.com/crowsonkb/k-diffusion.git", repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
+    git_clone("https://github.com/sczhou/CodeFormer.git", repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
+    git_clone("https://github.com/salesforce/BLIP.git", repo_dir('BLIP'), "BLIP", blip_commit_hash)
+
+    if not is_installed("lpips"):
+        run_pip(f"install -r {os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}", "requirements for CodeFormer")
+
+    run_pip(f"install -r {requirements_file}", "requirements for Web UI")
+
+    sys.argv += args
+
+    if "--exit" in args:
+        print("Exiting because of --exit argument")
+        exit(0)
 
-if "--exit" in args:
-    print("Exiting because of --exit argument")
-    exit(0)
 
 def start_webui():
     print(f"Launching Web UI with arguments: {' '.join(sys.argv[1:])}")
     import webui
     webui.webui()
 
+
 if __name__ == "__main__":
+    prepare_enviroment()
     start_webui()

modules/bsrgan_model.py

@@ -10,13 +10,11 @@ from basicsr.utils.download_util import load_file_from_url
 import modules.upscaler
 from modules import devices, modelloader
 from modules.bsrgan_model_arch import RRDBNet
-from modules.paths import models_path
 
 
 class UpscalerBSRGAN(modules.upscaler.Upscaler):
     def __init__(self, dirname):
         self.name = "BSRGAN"
-        self.model_path = os.path.join(models_path, self.name)
         self.model_name = "BSRGAN 4x"
         self.model_url = "https://github.com/cszn/KAIR/releases/download/v1.0/BSRGAN.pth"
         self.user_path = dirname

modules/deepbooru.py

@@ -0,0 +1,73 @@
+import os.path
+from concurrent.futures import ProcessPoolExecutor
+from multiprocessing import get_context
+
+
+def _load_tf_and_return_tags(pil_image, threshold):
+    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)
+        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"))
+
+    tags = dd.project.load_tags_from_project(model_path)
+    model = dd.project.load_model_from_project(
+        model_path, compile_model=True
+    )
+
+    width = model.input_shape[2]
+    height = model.input_shape[1]
+    image = np.array(pil_image)
+    image = tf.image.resize(
+        image,
+        size=(height, width),
+        method=tf.image.ResizeMethod.AREA,
+        preserve_aspect_ratio=True,
+    )
+    image = image.numpy()  # EagerTensor to np.array
+    image = dd.image.transform_and_pad_image(image, width, height)
+    image = image / 255.0
+    image_shape = image.shape
+    image = image.reshape((1, image_shape[0], image_shape[1], image_shape[2]))
+
+    y = model.predict(image)[0]
+
+    result_dict = {}
+
+    for i, tag in enumerate(tags):
+        result_dict[tag] = y[i]
+    result_tags_out = []
+    result_tags_print = []
+    for tag in tags:
+        if result_dict[tag] >= threshold:
+            if tag.startswith("rating:"):
+                continue
+            result_tags_out.append(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(':', ' ')
+
+
+def subprocess_init_no_cuda():
+    import os
+    os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+
+
+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

modules/esrgan_model.py

@@ -5,9 +5,8 @@ import torch
 from PIL import Image
 from basicsr.utils.download_util import load_file_from_url
 
-import modules.esrgam_model_arch as arch
+import modules.esrgan_model_arch as arch
 from modules import shared, modelloader, images, devices
-from modules.paths import models_path
 from modules.upscaler import Upscaler, UpscalerData
 from modules.shared import opts
 
@@ -76,7 +75,6 @@ class UpscalerESRGAN(Upscaler):
         self.model_name = "ESRGAN_4x"
         self.scalers = []
         self.user_path = dirname
-        self.model_path = os.path.join(models_path, self.name)
         super().__init__()
         model_paths = self.find_models(ext_filter=[".pt", ".pth"])
         scalers = []
@@ -111,7 +109,7 @@ class UpscalerESRGAN(Upscaler):
             print("Unable to load %s from %s" % (self.model_path, filename))
             return None
 
-        pretrained_net = torch.load(filename, map_location='cpu' if shared.device.type == 'mps' else None)
+        pretrained_net = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
         crt_model = arch.RRDBNet(3, 3, 64, 23, gc=32)
 
         pretrained_net = fix_model_layers(crt_model, pretrained_net)

modules/extras.py

@@ -98,6 +98,10 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v
                           no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo,
                           forced_filename=image_name if opts.use_original_name_batch else None)
 
+        if opts.enable_pnginfo:
+            image.info = existing_pnginfo
+            image.info["extras"] = info
+
         outputs.append(image)
 
     devices.torch_gc()
@@ -169,9 +173,9 @@ def run_modelmerger(primary_model_name, secondary_model_name, interp_method, int
 
     print(f"Loading {secondary_model_info.filename}...")
     secondary_model = torch.load(secondary_model_info.filename, map_location='cpu')
-   
-    theta_0 = primary_model['state_dict']
-    theta_1 = secondary_model['state_dict']
+
+    theta_0 = sd_models.get_state_dict_from_checkpoint(primary_model)
+    theta_1 = sd_models.get_state_dict_from_checkpoint(secondary_model)
 
     theta_funcs = {
         "Weighted Sum": weighted_sum,

modules/hypernetwork.py

@@ -40,27 +40,37 @@ class Hypernetwork:
             self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
 
 
-def load_hypernetworks(path):
+def list_hypernetworks(path):
     res = {}
-
-    for filename in glob.iglob(path + '**/*.pt', recursive=True):
-        try:
-            hn = Hypernetwork(filename)
-            res[hn.name] = hn
-        except Exception:
-            print(f"Error loading hypernetwork {filename}", file=sys.stderr)
-            print(traceback.format_exc(), file=sys.stderr)
-
+    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.selected_hypernetwork()
+    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:

modules/images.py

@@ -349,6 +349,38 @@ def get_next_sequence_number(path, basename):
 
 
 def save_image(image, path, basename, seed=None, prompt=None, extension='png', info=None, short_filename=False, no_prompt=False, grid=False, pnginfo_section_name='parameters', p=None, existing_info=None, forced_filename=None, suffix="", save_to_dirs=None):
+    '''Save an image.
+
+    Args:
+        image (`PIL.Image`):
+            The image to be saved.
+        path (`str`):
+            The directory to save the image. Note, the option `save_to_dirs` will make the image to be saved into a sub directory.
+        basename (`str`):
+            The base filename which will be applied to `filename pattern`.
+        seed, prompt, short_filename, 
+        extension (`str`):
+            Image file extension, default is `png`.
+        pngsectionname (`str`):
+            Specify the name of the section which `info` will be saved in.
+        info (`str` or `PngImagePlugin.iTXt`):
+            PNG info chunks.
+        existing_info (`dict`):
+            Additional PNG info. `existing_info == {pngsectionname: info, ...}`
+        no_prompt:
+            TODO I don't know its meaning.
+        p (`StableDiffusionProcessing`)
+        forced_filename (`str`):
+            If specified, `basename` and filename pattern will be ignored.
+        save_to_dirs (bool):
+            If true, the image will be saved into a subdirectory of `path`.
+
+    Returns: (fullfn, txt_fullfn)
+        fullfn (`str`):
+            The full path of the saved imaged.
+        txt_fullfn (`str` or None):
+            If a text file is saved for this image, this will be its full path. Otherwise None.
+    '''
     if short_filename or prompt is None or seed is None:
         file_decoration = ""
     elif opts.save_to_dirs:
@@ -424,7 +456,10 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
             piexif.insert(exif_bytes(), fullfn_without_extension + ".jpg")
 
     if opts.save_txt and info is not None:
-        with open(f"{fullfn_without_extension}.txt", "w", encoding="utf8") as file:
+        txt_fullfn = f"{fullfn_without_extension}.txt"
+        with open(txt_fullfn, "w", encoding="utf8") as file:
             file.write(info + "\n")
+    else:
+        txt_fullfn = None
 
-    return fullfn
+    return fullfn, txt_fullfn

modules/img2img.py

@@ -32,6 +32,8 @@ def process_batch(p, input_dir, output_dir, args):
 
     for i, image in enumerate(images):
         state.job = f"{i+1} out of {len(images)}"
+        if state.skipped:
+            state.skipped = False
 
         if state.interrupted:
             break

modules/interrogate.py

@@ -140,11 +140,11 @@ class InterrogateModels:
 
             res = caption
 
-            cilp_image = self.clip_preprocess(pil_image).unsqueeze(0).type(self.dtype).to(shared.device)
+            clip_image = self.clip_preprocess(pil_image).unsqueeze(0).type(self.dtype).to(shared.device)
 
             precision_scope = torch.autocast if shared.cmd_opts.precision == "autocast" else contextlib.nullcontext
             with torch.no_grad(), precision_scope("cuda"):
-                image_features = self.clip_model.encode_image(cilp_image).type(self.dtype)
+                image_features = self.clip_model.encode_image(clip_image).type(self.dtype)
 
                 image_features /= image_features.norm(dim=-1, keepdim=True)
 

modules/ldsr_model.py

@@ -7,13 +7,11 @@ from basicsr.utils.download_util import load_file_from_url
 from modules.upscaler import Upscaler, UpscalerData
 from modules.ldsr_model_arch import LDSR
 from modules import shared
-from modules.paths import models_path
 
 
 class UpscalerLDSR(Upscaler):
     def __init__(self, user_path):
         self.name = "LDSR"
-        self.model_path = os.path.join(models_path, self.name)
         self.user_path = user_path
         self.model_url = "https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1"
         self.yaml_url = "https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1"

modules/paths.py

@@ -12,6 +12,7 @@ possible_sd_paths = [os.path.join(script_path, 'repositories/stable-diffusion'),
 for possible_sd_path in possible_sd_paths:
     if os.path.exists(os.path.join(possible_sd_path, 'ldm/models/diffusion/ddpm.py')):
         sd_path = os.path.abspath(possible_sd_path)
+        break
 
 assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
 

modules/processing.py

@@ -46,6 +46,12 @@ def apply_color_correction(correction, image):
     return image
 
 
+def get_correct_sampler(p):
+    if isinstance(p, modules.processing.StableDiffusionProcessingTxt2Img):
+        return sd_samplers.samplers
+    elif isinstance(p, modules.processing.StableDiffusionProcessingImg2Img):
+        return sd_samplers.samplers_for_img2img
+
 class StableDiffusionProcessing:
     def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt="", styles=None, seed=-1, subseed=-1, subseed_strength=0, seed_resize_from_h=-1, seed_resize_from_w=-1, seed_enable_extras=True, sampler_index=0, batch_size=1, n_iter=1, steps=50, cfg_scale=7.0, width=512, height=512, restore_faces=False, tiling=False, do_not_save_samples=False, do_not_save_grid=False, extra_generation_params=None, overlay_images=None, negative_prompt=None, eta=None):
         self.sd_model = sd_model
@@ -123,6 +129,7 @@ class Processed:
         self.index_of_first_image = index_of_first_image
         self.styles = p.styles
         self.job_timestamp = state.job_timestamp
+        self.clip_skip = opts.CLIP_ignore_last_layers
 
         self.eta = p.eta
         self.ddim_discretize = p.ddim_discretize
@@ -169,6 +176,7 @@ class Processed:
             "infotexts": self.infotexts,
             "styles": self.styles,
             "job_timestamp": self.job_timestamp,
+            "clip_skip": self.clip_skip,
         }
 
         return json.dumps(obj)
@@ -266,14 +274,18 @@ def fix_seed(p):
 def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration=0, position_in_batch=0):
     index = position_in_batch + iteration * p.batch_size
 
+    clip_skip = getattr(p, 'clip_skip', opts.CLIP_ignore_last_layers)
+
     generation_params = {
         "Steps": p.steps,
-        "Sampler": sd_samplers.samplers[p.sampler_index].name,
+        "Sampler": get_correct_sampler(p)[p.sampler_index].name,
         "CFG scale": p.cfg_scale,
         "Seed": all_seeds[index],
         "Face restoration": (opts.face_restoration_model if p.restore_faces else None),
         "Size": f"{p.width}x{p.height}",
         "Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
+        "Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
+        "Hypernet": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.name.replace(',', '').replace(':', '')),
         "Batch size": (None if p.batch_size < 2 else p.batch_size),
         "Batch pos": (None if p.batch_size < 2 else position_in_batch),
         "Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
@@ -281,6 +293,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration
         "Seed resize from": (None if p.seed_resize_from_w == 0 or p.seed_resize_from_h == 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
         "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==0 else clip_skip,
     }
 
     generation_params.update(p.extra_generation_params)
@@ -312,6 +325,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
         os.makedirs(p.outpath_grids, exist_ok=True)
 
     modules.sd_hijack.model_hijack.apply_circular(p.tiling)
+    modules.sd_hijack.model_hijack.clear_comments()
 
     comments = {}
 
@@ -341,7 +355,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
     infotexts = []
     output_images = []
 
-    with torch.no_grad():
+    with torch.no_grad(), p.sd_model.ema_scope():
         with devices.autocast():
             p.init(all_prompts, all_seeds, all_subseeds)
 
@@ -349,6 +363,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             state.job_count = p.n_iter
 
         for n in range(p.n_iter):
+            if state.skipped:
+                state.skipped = False
+            
             if state.interrupted:
                 break
 
@@ -375,9 +392,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             with devices.autocast():
                 samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)
 
-            if state.interrupted:
+            if state.interrupted or state.skipped:
 
-                # if we are interruped, sample returns just noise
+                # if we are interrupted, sample returns just noise
                 # use the image collected previously in sampler loop
                 samples_ddim = shared.state.current_latent
 
@@ -436,7 +453,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
 
                 text = infotext(n, i)
                 infotexts.append(text)
-                image.info["parameters"] = text
+                if opts.enable_pnginfo:
+                    image.info["parameters"] = text
                 output_images.append(image)
 
             del x_samples_ddim 
@@ -455,7 +473,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             if opts.return_grid:
                 text = infotext()
                 infotexts.insert(0, text)
-                grid.info["parameters"] = text
+                if opts.enable_pnginfo:
+                    grid.info["parameters"] = text
                 output_images.insert(0, grid)
                 index_of_first_image = 1
 

modules/prompt_parser.py

@@ -13,13 +13,14 @@ import lark
 
 schedule_parser = lark.Lark(r"""
 !start: (prompt | /[][():]/+)*
-prompt: (emphasized | scheduled | plain | WHITESPACE)*
+prompt: (emphasized | scheduled | alternate | plain | WHITESPACE)*
 !emphasized: "(" prompt ")"
         | "(" prompt ":" prompt ")"
         | "[" prompt "]"
 scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER "]"
+alternate: "[" prompt ("|" prompt)+ "]"
 WHITESPACE: /\s+/
-plain: /([^\\\[\]():]|\\.)+/
+plain: /([^\\\[\]():|]|\\.)+/
 %import common.SIGNED_NUMBER -> NUMBER
 """)
 
@@ -59,6 +60,8 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
                     tree.children[-1] *= steps
                 tree.children[-1] = min(steps, int(tree.children[-1]))
                 l.append(tree.children[-1])
+            def alternate(self, tree):
+                l.extend(range(1, steps+1))
         CollectSteps().visit(tree)
         return sorted(set(l))
 
@@ -67,6 +70,8 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
             def scheduled(self, args):
                 before, after, _, when = args
                 yield before or () if step <= when else after
+            def alternate(self, args):
+                yield next(args[(step - 1)%len(args)])
             def start(self, args):
                 def flatten(x):
                     if type(x) == str:
@@ -239,6 +244,15 @@ def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step):
 
         conds_list.append(conds_for_batch)
 
+    # if prompts have wildly different lengths above the limit we'll get tensors fo different shapes
+    # and won't be able to torch.stack them. So this fixes that.
+    token_count = max([x.shape[0] for x in tensors])
+    for i in range(len(tensors)):
+        if tensors[i].shape[0] != token_count:
+            last_vector = tensors[i][-1:]
+            last_vector_repeated = last_vector.repeat([token_count - tensors[i].shape[0], 1])
+            tensors[i] = torch.vstack([tensors[i], last_vector_repeated])
+
     return conds_list, torch.stack(tensors).to(device=param.device, dtype=param.dtype)
 
 

modules/realesrgan_model.py

@@ -8,14 +8,12 @@ from basicsr.utils.download_util import load_file_from_url
 from realesrgan import RealESRGANer
 
 from modules.upscaler import Upscaler, UpscalerData
-from modules.paths import models_path
 from modules.shared import cmd_opts, opts
 
 
 class UpscalerRealESRGAN(Upscaler):
     def __init__(self, path):
         self.name = "RealESRGAN"
-        self.model_path = os.path.join(models_path, self.name)
         self.user_path = path
         super().__init__()
         try:

modules/scunet_model.py

@@ -9,14 +9,12 @@ from basicsr.utils.download_util import load_file_from_url
 
 import modules.upscaler
 from modules import devices, modelloader
-from modules.paths import models_path
 from modules.scunet_model_arch import SCUNet as net
 
 
 class UpscalerScuNET(modules.upscaler.Upscaler):
     def __init__(self, dirname):
         self.name = "ScuNET"
-        self.model_path = os.path.join(models_path, self.name)
         self.model_name = "ScuNET GAN"
         self.model_name2 = "ScuNET PSNR"
         self.model_url = "https://github.com/cszn/KAIR/releases/download/v1.0/scunet_color_real_gan.pth"

modules/scunet_model_arch.py

@@ -40,7 +40,7 @@ class WMSA(nn.Module):
         Returns:
             attn_mask: should be (1 1 w p p),
         """
-        # supporting sqaure.
+        # supporting square.
         attn_mask = torch.zeros(h, w, p, p, p, p, dtype=torch.bool, device=self.relative_position_params.device)
         if self.type == 'W':
             return attn_mask
@@ -65,7 +65,7 @@ class WMSA(nn.Module):
         x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size)
         h_windows = x.size(1)
         w_windows = x.size(2)
-        # sqaure validation
+        # square validation
         # assert h_windows == w_windows
 
         x = rearrange(x, 'b w1 w2 p1 p2 c -> b (w1 w2) (p1 p2) c', p1=self.window_size, p2=self.window_size)

modules/sd_hijack.py

@@ -18,15 +18,20 @@ attention_CrossAttention_forward = ldm.modules.attention.CrossAttention.forward
 diffusionmodules_model_nonlinearity = ldm.modules.diffusionmodules.model.nonlinearity
 diffusionmodules_model_AttnBlock_forward = ldm.modules.diffusionmodules.model.AttnBlock.forward
 
-
 def apply_optimizations():
     undo_optimizations()
 
     ldm.modules.diffusionmodules.model.nonlinearity = silu
 
-    if cmd_opts.opt_split_attention_v1:
+    if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and torch.cuda.get_device_capability(shared.device) == (8, 6)):
+        print("Applying xformers cross attention optimization.")
+        ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
+        ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
+    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 or torch.cuda.is_available()):
+        print("Applying cross attention optimization.")
         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
 
@@ -37,6 +42,13 @@ def undo_optimizations():
     ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
 
 
+def get_target_prompt_token_count(token_count):
+    if token_count < 75:
+        return 75
+
+    return math.ceil(token_count / 10) * 10
+
+
 class StableDiffusionModelHijack:
     fixes = None
     comments = []
@@ -82,10 +94,12 @@ class StableDiffusionModelHijack:
         for layer in [layer for layer in self.layers if type(layer) == torch.nn.Conv2d]:
             layer.padding_mode = 'circular' if enable else 'zeros'
 
+    def clear_comments(self):
+        self.comments = []
+
     def tokenize(self, text):
-        max_length = self.clip.max_length - 2
         _, remade_batch_tokens, _, _, _, token_count = self.clip.process_text([text])
-        return remade_batch_tokens[0], token_count, max_length
+        return remade_batch_tokens[0], token_count, get_target_prompt_token_count(token_count)
 
 
 class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
@@ -94,7 +108,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
         self.wrapped = wrapped
         self.hijack: StableDiffusionModelHijack = hijack
         self.tokenizer = wrapped.tokenizer
-        self.max_length = wrapped.max_length
         self.token_mults = {}
 
         tokens_with_parens = [(k, v) for k, v in self.tokenizer.get_vocab().items() if '(' in k or ')' in k or '[' in k or ']' in k]
@@ -116,7 +129,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
     def tokenize_line(self, line, used_custom_terms, hijack_comments):
         id_start = self.wrapped.tokenizer.bos_token_id
         id_end = self.wrapped.tokenizer.eos_token_id
-        maxlen = self.wrapped.max_length
 
         if opts.enable_emphasis:
             parsed = prompt_parser.parse_prompt_attention(line)
@@ -148,19 +160,12 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
                     used_custom_terms.append((embedding.name, embedding.checksum()))
                     i += embedding_length_in_tokens
 
-        if len(remade_tokens) > maxlen - 2:
-            vocab = {v: k for k, v in self.wrapped.tokenizer.get_vocab().items()}
-            ovf = remade_tokens[maxlen - 2:]
-            overflowing_words = [vocab.get(int(x), "") for x in ovf]
-            overflowing_text = self.wrapped.tokenizer.convert_tokens_to_string(''.join(overflowing_words))
-            hijack_comments.append(f"Warning: too many input tokens; some ({len(overflowing_words)}) have been truncated:\n{overflowing_text}\n")
-
         token_count = len(remade_tokens)
-        remade_tokens = remade_tokens + [id_end] * (maxlen - 2 - len(remade_tokens))
-        remade_tokens = [id_start] + remade_tokens[0:maxlen - 2] + [id_end]
+        prompt_target_length = get_target_prompt_token_count(token_count)
+        tokens_to_add = prompt_target_length - len(remade_tokens) + 1
 
-        multipliers = multipliers + [1.0] * (maxlen - 2 - len(multipliers))
-        multipliers = [1.0] + multipliers[0:maxlen - 2] + [1.0]
+        remade_tokens = [id_start] + remade_tokens + [id_end] * tokens_to_add
+        multipliers = [1.0] + multipliers + [1.0] * tokens_to_add
 
         return remade_tokens, fixes, multipliers, token_count
 
@@ -177,7 +182,8 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
             if line in cache:
                 remade_tokens, fixes, multipliers = cache[line]
             else:
-                remade_tokens, fixes, multipliers, token_count = self.tokenize_line(line, used_custom_terms, hijack_comments)
+                remade_tokens, fixes, multipliers, current_token_count = self.tokenize_line(line, used_custom_terms, hijack_comments)
+                token_count = max(current_token_count, token_count)
 
                 cache[line] = (remade_tokens, fixes, multipliers)
 
@@ -191,7 +197,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
     def process_text_old(self, text):
         id_start = self.wrapped.tokenizer.bos_token_id
         id_end = self.wrapped.tokenizer.eos_token_id
-        maxlen = self.wrapped.max_length
+        maxlen = self.wrapped.max_length  # you get to stay at 77
         used_custom_terms = []
         remade_batch_tokens = []
         overflowing_words = []
@@ -263,17 +269,31 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
             batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count = self.process_text(text)
 
         self.hijack.fixes = hijack_fixes
-        self.hijack.comments = hijack_comments
+        self.hijack.comments += hijack_comments
 
         if len(used_custom_terms) > 0:
             self.hijack.comments.append("Used embeddings: " + ", ".join([f'{word} [{checksum}]' for word, checksum in used_custom_terms]))
 
-        tokens = torch.asarray(remade_batch_tokens).to(device)
-        outputs = self.wrapped.transformer(input_ids=tokens)
-        z = outputs.last_hidden_state
+        target_token_count = get_target_prompt_token_count(token_count) + 2
+
+        position_ids_array = [min(x, 75) for x in range(target_token_count-1)] + [76]
+        position_ids = torch.asarray(position_ids_array, device=devices.device).expand((1, -1))
+
+        remade_batch_tokens_of_same_length = [x + [self.wrapped.tokenizer.eos_token_id] * (target_token_count - len(x)) for x in remade_batch_tokens]
+        tokens = torch.asarray(remade_batch_tokens_of_same_length).to(device)
+
+        tmp = -opts.CLIP_ignore_last_layers
+        if (opts.CLIP_ignore_last_layers == 0):
+            outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids)
+            z = outputs.last_hidden_state
+        else:
+            outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids, output_hidden_states=tmp)
+            z = outputs.hidden_states[tmp]
+            z = self.wrapped.transformer.text_model.final_layer_norm(z)
 
         # restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
-        batch_multipliers = torch.asarray(batch_multipliers).to(device)
+        batch_multipliers_of_same_length = [x + [1.0] * (target_token_count - len(x)) for x in batch_multipliers]
+        batch_multipliers = torch.asarray(batch_multipliers_of_same_length).to(device)
         original_mean = z.mean()
         z *= batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)
         new_mean = z.mean()

modules/sd_hijack_optimizations.py

@@ -1,4 +1,7 @@
 import math
+import sys
+import traceback
+
 import torch
 from torch import einsum
 
@@ -7,18 +10,37 @@ from einops import rearrange
 
 from modules import shared
 
+if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers:
+    try:
+        import xformers.ops
+        import functorch
+        xformers._is_functorch_available = True
+        shared.xformers_available = True
+    except Exception:
+        print("Cannot import xformers", file=sys.stderr)
+        print(traceback.format_exc(), file=sys.stderr)
+
 
 # see https://github.com/basujindal/stable-diffusion/pull/117 for discussion
 def split_cross_attention_forward_v1(self, x, context=None, mask=None):
     h = self.heads
 
-    q = self.to_q(x)
+    q_in = self.to_q(x)
     context = default(context, x)
-    k = self.to_k(context)
-    v = self.to_v(context)
+
+    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
 
-    q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
+    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
 
     r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device)
     for i in range(0, q.shape[0], 2):
@@ -31,6 +53,7 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
 
         r1[i:end] = einsum('b i j, b j d -> b i d', s2, v[i:end])
         del s2
+    del q, k, v
 
     r2 = rearrange(r1, '(b h) n d -> b n (h d)', h=h)
     del r1
@@ -45,7 +68,7 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
     q_in = self.to_q(x)
     context = default(context, x)
 
-    hypernetwork = shared.selected_hypernetwork()
+    hypernetwork = shared.loaded_hypernetwork
     hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
 
     if hypernetwork_layers is not None:
@@ -105,6 +128,25 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
 
     return self.to_out(r2)
 
+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)
+    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)
+
+    out = rearrange(out, 'b n h d -> b n (h d)', h=h)
+    return self.to_out(out)
+
 def cross_attention_attnblock_forward(self, x):
         h_ = x
         h_ = self.norm(h_)
@@ -167,3 +209,16 @@ def cross_attention_attnblock_forward(self, x):
         h3 += x
 
         return h3
+    
+def xformers_attnblock_forward(self, x):
+    try:
+        h_ = x
+        h_ = self.norm(h_)
+        q1 = self.q(h_).contiguous()
+        k1 = self.k(h_).contiguous()
+        v = self.v(h_).contiguous()
+        out = xformers.ops.memory_efficient_attention(q1, k1, v)
+        out = self.proj_out(out)
+        return x + out
+    except NotImplementedError:
+        return cross_attention_attnblock_forward(self, x)

modules/sd_models.py

@@ -5,7 +5,6 @@ from collections import namedtuple
 import torch
 from omegaconf import OmegaConf
 
-
 from ldm.util import instantiate_from_config
 
 from modules import shared, modelloader, devices
@@ -14,7 +13,7 @@ from modules.paths import models_path
 model_dir = "Stable-diffusion"
 model_path = os.path.abspath(os.path.join(models_path, model_dir))
 
-CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash', 'model_name'])
+CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash', 'model_name', 'config'])
 checkpoints_list = {}
 
 try:
@@ -63,14 +62,20 @@ def list_models():
     if os.path.exists(cmd_ckpt):
         h = model_hash(cmd_ckpt)
         title, short_model_name = modeltitle(cmd_ckpt, h)
-        checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h, short_model_name)
+        checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h, short_model_name, shared.cmd_opts.config)
         shared.opts.data['sd_model_checkpoint'] = title
     elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file:
         print(f"Checkpoint in --ckpt argument not found (Possible it was moved to {model_path}: {cmd_ckpt}", file=sys.stderr)
     for filename in model_list:
         h = model_hash(filename)
         title, short_model_name = modeltitle(filename, h)
-        checkpoints_list[title] = CheckpointInfo(filename, title, h, short_model_name)
+
+        basename, _ = os.path.splitext(filename)
+        config = basename + ".yaml"
+        if not os.path.exists(config):
+            config = shared.cmd_opts.config
+
+        checkpoints_list[title] = CheckpointInfo(filename, title, h, short_model_name, config)
 
 
 def get_closet_checkpoint_match(searchString):
@@ -116,13 +121,24 @@ def select_checkpoint():
     return checkpoint_info
 
 
-def load_model_weights(model, checkpoint_file, sd_model_hash):
+def get_state_dict_from_checkpoint(pl_sd):
+    if "state_dict" in pl_sd:
+        return pl_sd["state_dict"]
+
+    return pl_sd
+
+
+def load_model_weights(model, checkpoint_info):
+    checkpoint_file = checkpoint_info.filename
+    sd_model_hash = checkpoint_info.hash
+
     print(f"Loading weights [{sd_model_hash}] from {checkpoint_file}")
 
     pl_sd = torch.load(checkpoint_file, map_location="cpu")
     if "global_step" in pl_sd:
         print(f"Global Step: {pl_sd['global_step']}")
-    sd = pl_sd["state_dict"]
+
+    sd = get_state_dict_from_checkpoint(pl_sd)
 
     model.load_state_dict(sd, strict=False)
 
@@ -143,16 +159,20 @@ def load_model_weights(model, checkpoint_file, sd_model_hash):
         model.first_stage_model.load_state_dict(vae_dict)
 
     model.sd_model_hash = sd_model_hash
-    model.sd_model_checkpint = checkpoint_file
+    model.sd_model_checkpoint = checkpoint_file
+    model.sd_checkpoint_info = checkpoint_info
 
 
 def load_model():
     from modules import lowvram, sd_hijack
     checkpoint_info = select_checkpoint()
 
-    sd_config = OmegaConf.load(shared.cmd_opts.config)
+    if checkpoint_info.config != shared.cmd_opts.config:
+        print(f"Loading config from: {checkpoint_info.config}")
+
+    sd_config = OmegaConf.load(checkpoint_info.config)
     sd_model = instantiate_from_config(sd_config.model)
-    load_model_weights(sd_model, checkpoint_info.filename, checkpoint_info.hash)
+    load_model_weights(sd_model, checkpoint_info)
 
     if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
         lowvram.setup_for_low_vram(sd_model, shared.cmd_opts.medvram)
@@ -171,9 +191,13 @@ def reload_model_weights(sd_model, info=None):
     from modules import lowvram, devices, sd_hijack
     checkpoint_info = info or select_checkpoint()
 
-    if sd_model.sd_model_checkpint == checkpoint_info.filename:
+    if sd_model.sd_model_checkpoint == checkpoint_info.filename:
         return
 
+    if sd_model.sd_checkpoint_info.config != checkpoint_info.config:
+        shared.sd_model = load_model()
+        return shared.sd_model
+
     if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
         lowvram.send_everything_to_cpu()
     else:
@@ -181,7 +205,7 @@ def reload_model_weights(sd_model, info=None):
 
     sd_hijack.model_hijack.undo_hijack(sd_model)
 
-    load_model_weights(sd_model, checkpoint_info.filename, checkpoint_info.hash)
+    load_model_weights(sd_model, checkpoint_info)
 
     sd_hijack.model_hijack.hijack(sd_model)
 

modules/sd_samplers.py

@@ -106,7 +106,7 @@ def extended_tdqm(sequence, *args, desc=None, **kwargs):
     seq = sequence if cmd_opts.disable_console_progressbars else tqdm.tqdm(sequence, *args, desc=state.job, file=shared.progress_print_out, **kwargs)
 
     for x in seq:
-        if state.interrupted:
+        if state.interrupted or state.skipped:
             break
 
         yield x
@@ -142,6 +142,16 @@ class VanillaStableDiffusionSampler:
         assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers'
         cond = tensor
 
+        # for DDIM, shapes must match, we can't just process cond and uncond independently;
+        # filling unconditional_conditioning with repeats of the last vector to match length is
+        # not 100% correct but should work well enough
+        if unconditional_conditioning.shape[1] < cond.shape[1]:
+            last_vector = unconditional_conditioning[:, -1:]
+            last_vector_repeated = last_vector.repeat([1, cond.shape[1] - unconditional_conditioning.shape[1], 1])
+            unconditional_conditioning = torch.hstack([unconditional_conditioning, last_vector_repeated])
+        elif unconditional_conditioning.shape[1] > cond.shape[1]:
+            unconditional_conditioning = unconditional_conditioning[:, :cond.shape[1]]
+
         if self.mask is not None:
             img_orig = self.sampler.model.q_sample(self.init_latent, ts)
             x_dec = img_orig * self.mask + self.nmask * x_dec
@@ -171,7 +181,7 @@ class VanillaStableDiffusionSampler:
 
         self.initialize(p)
 
-        # existing code fails with cetain step counts, like 9
+        # existing code fails with certain step counts, like 9
         try:
             self.sampler.make_schedule(ddim_num_steps=steps,  ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False)
         except Exception:
@@ -194,7 +204,7 @@ class VanillaStableDiffusionSampler:
 
         steps = steps or p.steps
 
-        # existing code fails with cetin step counts, like 9
+        # existing code fails with certain step counts, like 9
         try:
             samples_ddim, _ = self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)
         except Exception:
@@ -221,18 +231,29 @@ class CFGDenoiser(torch.nn.Module):
 
         x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
         sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
-        cond_in = torch.cat([tensor, uncond])
 
-        if shared.batch_cond_uncond:
-            x_out = self.inner_model(x_in, sigma_in, cond=cond_in)
+        if tensor.shape[1] == uncond.shape[1]:
+            cond_in = torch.cat([tensor, uncond])
+
+            if shared.batch_cond_uncond:
+                x_out = self.inner_model(x_in, sigma_in, cond=cond_in)
+            else:
+                x_out = torch.zeros_like(x_in)
+                for batch_offset in range(0, x_out.shape[0], batch_size):
+                    a = batch_offset
+                    b = a + batch_size
+                    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=cond_in[a:b])
         else:
             x_out = torch.zeros_like(x_in)
-            for batch_offset in range(0, x_out.shape[0], batch_size):
+            batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
+            for batch_offset in range(0, tensor.shape[0], batch_size):
                 a = batch_offset
-                b = a + batch_size
-                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=cond_in[a:b])
+                b = min(a + batch_size, tensor.shape[0])
+                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=tensor[a:b])
 
-        denoised_uncond = x_out[-batch_size:]
+            x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=uncond)
+
+        denoised_uncond = x_out[-uncond.shape[0]:]
         denoised = torch.clone(denoised_uncond)
 
         for i, conds in enumerate(conds_list):
@@ -254,7 +275,7 @@ def extended_trange(sampler, count, *args, **kwargs):
     seq = range(count) if cmd_opts.disable_console_progressbars else tqdm.trange(count, *args, desc=state.job, file=shared.progress_print_out, **kwargs)
 
     for x in seq:
-        if state.interrupted:
+        if state.interrupted or state.skipped:
             break
 
         if sampler.stop_at is not None and x > sampler.stop_at:

modules/shared.py

@@ -43,6 +43,9 @@ parser.add_argument("--realesrgan-models-path", type=str, help="Path to director
 parser.add_argument("--scunet-models-path", type=str, help="Path to directory with ScuNET model file(s).", default=os.path.join(models_path, 'ScuNET'))
 parser.add_argument("--swinir-models-path", type=str, help="Path to directory with SwinIR model file(s).", default=os.path.join(models_path, 'SwinIR'))
 parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with LDSR model file(s).", default=os.path.join(models_path, 'LDSR'))
+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-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
@@ -73,17 +76,15 @@ device = devices.device
 
 batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)
 parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
-
+xformers_available = False
 config_filename = cmd_opts.ui_settings_file
 
-hypernetworks = hypernetwork.load_hypernetworks(os.path.join(models_path, 'hypernetworks'))
-
-
-def selected_hypernetwork():
-    return hypernetworks.get(opts.sd_hypernetwork, None)
+hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks'))
+loaded_hypernetwork = None
 
 
 class State:
+    skipped = False
     interrupted = False
     job = ""
     job_no = 0
@@ -96,6 +97,9 @@ class State:
     current_image_sampling_step = 0
     textinfo = None
 
+    def skip(self):
+        self.skipped = True
+
     def interrupt(self):
         self.interrupted = True
 
@@ -118,8 +122,6 @@ prompt_styles = modules.styles.StyleDatabase(styles_filename)
 interrogator = modules.interrogate.InterrogateModels("interrogate")
 
 face_restorers = []
-# This was moved to webui.py with the other model "setup" calls.
-# modules.sd_models.list_models()
 
 
 def realesrgan_models_names():
@@ -137,9 +139,9 @@ class OptionInfo:
         self.section = None
 
 
-def options_section(section_identifer, options_dict):
+def options_section(section_identifier, options_dict):
     for k, v in options_dict.items():
-        v.section = section_identifer
+        v.section = section_identifier
 
     return options_dict
 
@@ -221,6 +223,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
     "enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),
     "filter_nsfw": OptionInfo(False, "Filter NSFW content"),
+    'CLIP_ignore_last_layers': OptionInfo(0, "Ignore last layers of CLIP model", gr.Slider, {"minimum": 0, "maximum": 5, "step": 1}),
     "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
 }))
 
@@ -235,13 +238,14 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
 
 options_templates.update(options_section(('ui', "User interface"), {
     "show_progressbar": OptionInfo(True, "Show progressbar"),
-    "show_progress_every_n_steps": OptionInfo(0, "Show show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),
+    "show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),
     "return_grid": OptionInfo(True, "Show grid in results for web"),
     "do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
     "add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
+    "add_model_name_to_info": OptionInfo(False, "Add model name to generation information"),
     "font": OptionInfo("", "Font for image grids that have text"),
     "js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),
-    "js_modal_lightbox_initialy_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
+    "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
     "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
 }))
 

modules/swinir_model.py

@@ -8,7 +8,6 @@ from basicsr.utils.download_util import load_file_from_url
 from tqdm import tqdm
 
 from modules import modelloader
-from modules.paths import models_path
 from modules.shared import cmd_opts, opts, device
 from modules.swinir_model_arch import SwinIR as net
 from modules.upscaler import Upscaler, UpscalerData
@@ -25,7 +24,6 @@ class UpscalerSwinIR(Upscaler):
                          "/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR" \
                          "-L_x4_GAN.pth "
         self.model_name = "SwinIR 4x"
-        self.model_path = os.path.join(models_path, self.name)
         self.user_path = dirname
         super().__init__()
         scalers = []

modules/swinir_model_arch.py

@@ -166,7 +166,7 @@ class SwinTransformerBlock(nn.Module):
 
     Args:
         dim (int): Number of input channels.
-        input_resolution (tuple[int]): Input resulotion.
+        input_resolution (tuple[int]): Input resolution.
         num_heads (int): Number of attention heads.
         window_size (int): Window size.
         shift_size (int): Shift size for SW-MSA.

modules/ui.py

@@ -25,6 +25,8 @@ import gradio.routes
 from modules import sd_hijack
 from modules.paths import script_path
 from modules.shared import opts, cmd_opts
+if cmd_opts.deepdanbooru:
+    from modules.deepbooru import get_deepbooru_tags
 import modules.shared as shared
 from modules.sd_samplers import samplers, samplers_for_img2img
 from modules.sd_hijack import model_hijack
@@ -38,7 +40,7 @@ from modules import prompt_parser
 from modules.images import save_image
 import modules.textual_inversion.ui
 
-# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the bowser will not show any UI
+# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI
 mimetypes.init()
 mimetypes.add_type('application/javascript', '.js')
 
@@ -98,11 +100,12 @@ def send_gradio_gallery_to_image(x):
     return image_from_url_text(x[0])
 
 
-def save_files(js_data, images, index):
+def save_files(js_data, images, do_make_zip, index):
     import csv    
     filenames = []
+    fullfns = []
 
-    #quick dictionary to class object conversion. Its neccesary due apply_filename_pattern requiring it
+    #quick dictionary to class object conversion. Its necessary due apply_filename_pattern requiring it
     class MyObject:
         def __init__(self, d=None):
             if d is not None:
@@ -137,14 +140,29 @@ def save_files(js_data, images, index):
             is_grid = image_index < p.index_of_first_image
             i = 0 if is_grid else (image_index - p.index_of_first_image)
 
-            fullfn = save_image(image, path, "", seed=p.all_seeds[i], prompt=p.all_prompts[i], extension=extension, info=p.infotexts[image_index], grid=is_grid, p=p, save_to_dirs=save_to_dirs)
+            fullfn, txt_fullfn = save_image(image, path, "", seed=p.all_seeds[i], prompt=p.all_prompts[i], extension=extension, info=p.infotexts[image_index], grid=is_grid, p=p, save_to_dirs=save_to_dirs)
 
             filename = os.path.relpath(fullfn, path)
             filenames.append(filename)
+            fullfns.append(fullfn)
+            if txt_fullfn:
+                filenames.append(os.path.basename(txt_fullfn))
+                fullfns.append(txt_fullfn)
 
         writer.writerow([data["prompt"], data["seed"], data["width"], data["height"], data["sampler"], data["cfg_scale"], data["steps"], filenames[0], data["negative_prompt"]])
 
-    return '', '', plaintext_to_html(f"Saved: {filenames[0]}")
+    # Make Zip
+    if do_make_zip:
+        zip_filepath = os.path.join(path, "images.zip")
+
+        from zipfile import ZipFile
+        with ZipFile(zip_filepath, "w") as zip_file:
+            for i in range(len(fullfns)):
+                with open(fullfns[i], mode="rb") as f:
+                    zip_file.writestr(filenames[i], f.read())
+        fullfns.insert(0, zip_filepath)
+
+    return gr.File.update(value=fullfns, visible=True), '', '', plaintext_to_html(f"Saved: {filenames[0]}")
 
 
 def wrap_gradio_call(func, extra_outputs=None):
@@ -191,6 +209,7 @@ def wrap_gradio_call(func, extra_outputs=None):
         # last item is always HTML
         res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed_text}</p>{vram_html}</div>"
 
+        shared.state.skipped = False
         shared.state.interrupted = False
         shared.state.job_count = 0
 
@@ -291,6 +310,11 @@ def interrogate(image):
     return gr_show(True) if prompt is None else prompt
 
 
+def interrogate_deepbooru(image):
+    prompt = get_deepbooru_tags(image)
+    return gr_show(True) if prompt is None else prompt
+
+
 def create_seed_inputs():
     with gr.Row():
         with gr.Box():
@@ -411,24 +435,36 @@ def create_toprow(is_img2img):
 
         with gr.Column(scale=1):
             with gr.Row():
+                skip = gr.Button('Skip', elem_id=f"{id_part}_skip")
                 interrupt = gr.Button('Interrupt', elem_id=f"{id_part}_interrupt")
                 submit = gr.Button('Generate', elem_id=f"{id_part}_generate", variant='primary')
 
+                skip.click(
+                    fn=lambda: shared.state.skip(),
+                    inputs=[],
+                    outputs=[],
+                )
+
                 interrupt.click(
                     fn=lambda: shared.state.interrupt(),
                     inputs=[],
                     outputs=[],
                 )
 
-            with gr.Row():
+            with gr.Row(scale=1):
                 if is_img2img:
-                    interrogate = gr.Button('Interrogate', elem_id="interrogate")
+                    interrogate = gr.Button('Interrogate\nCLIP', elem_id="interrogate")
+                    if cmd_opts.deepdanbooru:
+                        deepbooru = gr.Button('Interrogate\nDeepBooru', elem_id="deepbooru")
+                    else:
+                        deepbooru = None
                 else:
                     interrogate = None
+                    deepbooru = None
                 prompt_style_apply = gr.Button('Apply style', elem_id="style_apply")
                 save_style = gr.Button('Create style', elem_id="style_create")
 
-    return prompt, roll, prompt_style, negative_prompt, prompt_style2, submit, interrogate, prompt_style_apply, save_style, paste, token_counter, token_button
+    return prompt, roll, prompt_style, negative_prompt, prompt_style2, submit, interrogate, deepbooru, prompt_style_apply, save_style, paste, token_counter, token_button
 
 
 def setup_progressbar(progressbar, preview, id_part, textinfo=None):
@@ -457,7 +493,7 @@ def create_ui(wrap_gradio_gpu_call):
     import modules.txt2img
 
     with gr.Blocks(analytics_enabled=False) as txt2img_interface:
-        txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, txt2img_prompt_style_apply, txt2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=False)
+        txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _, txt2img_prompt_style_apply, txt2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=False)
         dummy_component = gr.Label(visible=False)
 
         with gr.Row(elem_id='txt2img_progress_row'):
@@ -513,6 +549,12 @@ def create_ui(wrap_gradio_gpu_call):
                         button_id = "hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder'
                         open_txt2img_folder = gr.Button(folder_symbol, elem_id=button_id)
 
+                    with gr.Row():
+                        do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False)
+                    
+                    with gr.Row():
+                        download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
+
                 with gr.Group():
                     html_info = gr.HTML()
                     generation_info = gr.Textbox(visible=False)
@@ -562,13 +604,15 @@ def create_ui(wrap_gradio_gpu_call):
 
             save.click(
                 fn=wrap_gradio_call(save_files),
-                _js="(x, y, z) => [x, y, selected_gallery_index()]",
+                _js="(x, y, z, w) => [x, y, z, selected_gallery_index()]",
                 inputs=[
                     generation_info,
                     txt2img_gallery,
+                    do_make_zip,
                     html_info,
                 ],
                 outputs=[
+                    download_files,
                     html_info,
                     html_info,
                     html_info,
@@ -609,7 +653,7 @@ def create_ui(wrap_gradio_gpu_call):
             token_button.click(fn=update_token_counter, inputs=[txt2img_prompt, steps], outputs=[token_counter])
 
     with gr.Blocks(analytics_enabled=False) as img2img_interface:
-        img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_prompt_style_apply, img2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=True)
+        img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=True)
 
         with gr.Row(elem_id='img2img_progress_row'):
             with gr.Column(scale=1):
@@ -693,6 +737,12 @@ def create_ui(wrap_gradio_gpu_call):
                         button_id = "hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder'
                         open_img2img_folder = gr.Button(folder_symbol, elem_id=button_id)
 
+                    with gr.Row():
+                        do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False)
+                    
+                    with gr.Row():
+                        download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
+
                 with gr.Group():
                     html_info = gr.HTML()
                     generation_info = gr.Textbox(visible=False)
@@ -766,15 +816,24 @@ def create_ui(wrap_gradio_gpu_call):
                 outputs=[img2img_prompt],
             )
 
+            if cmd_opts.deepdanbooru:
+                img2img_deepbooru.click(
+                    fn=interrogate_deepbooru,
+                    inputs=[init_img],
+                    outputs=[img2img_prompt],
+                )
+
             save.click(
                 fn=wrap_gradio_call(save_files),
-                _js="(x, y, z) => [x, y, selected_gallery_index()]",
+                _js="(x, y, z, w) => [x, y, z, selected_gallery_index()]",
                 inputs=[
                     generation_info,
                     img2img_gallery,
-                    html_info
+                    do_make_zip,
+                    html_info,
                 ],
                 outputs=[
+                    download_files,
                     html_info,
                     html_info,
                     html_info,
@@ -938,7 +997,7 @@ def create_ui(wrap_gradio_gpu_call):
                 custom_name = gr.Textbox(label="Custom Name (Optional)")
                 interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Interpolation Amount', value=0.3)
                 interp_method = gr.Radio(choices=["Weighted Sum", "Sigmoid", "Inverse Sigmoid"], value="Weighted Sum", label="Interpolation Method")
-                save_as_half = gr.Checkbox(value=False, label="Safe as float16")
+                save_as_half = gr.Checkbox(value=False, label="Save as float16")
                 modelmerger_merge = gr.Button(elem_id="modelmerger_merge", label="Merge", variant='primary')
 
             with gr.Column(variant='panel'):
@@ -972,9 +1031,9 @@ def create_ui(wrap_gradio_gpu_call):
                     process_dst = gr.Textbox(label='Destination directory')
 
                     with gr.Row():
-                        process_flip = gr.Checkbox(label='Flip')
-                        process_split = gr.Checkbox(label='Split into two')
-                        process_caption = gr.Checkbox(label='Add caption')
+                        process_flip = gr.Checkbox(label='Create flipped copies')
+                        process_split = gr.Checkbox(label='Split oversized images into two')
+                        process_caption = gr.Checkbox(label='Use BLIP caption as filename')
 
                     with gr.Row():
                         with gr.Column(scale=3):
@@ -1094,6 +1153,15 @@ def create_ui(wrap_gradio_gpu_call):
     component_dict = {}
 
     def open_folder(f):
+        if not os.path.isdir(f):
+            print(f"""
+WARNING
+An open_folder request was made with an argument that is not a folder.
+This could be an error or a malicious attempt to run code on your computer.
+Requested path was: {f}
+""", file=sys.stderr)
+            return
+
         if not shared.cmd_opts.hide_ui_dir_config:
             path = os.path.normpath(f)
             if platform.system() == "Windows":

modules/upscaler.py

@@ -36,10 +36,11 @@ class Upscaler:
         self.half = not modules.shared.cmd_opts.no_half
         self.pre_pad = 0
         self.mod_scale = None
-        if self.name is not None and create_dirs:
+
+        if self.model_path is None and self.name:
             self.model_path = os.path.join(models_path, self.name)
-            if not os.path.exists(self.model_path):
-                os.makedirs(self.model_path)
+        if self.model_path and create_dirs:
+            os.makedirs(self.model_path, exist_ok=True)
 
         try:
             import cv2

requirements.txt

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

requirements_versions.txt

@@ -22,3 +22,4 @@ resize-right==0.0.2
 torchdiffeq==0.2.3
 kornia==0.6.7
 lark==1.1.2
+functorch==0.2.1

scripts/prompts_from_file.py

@@ -10,7 +10,6 @@ from modules.processing import Processed, process_images
 from PIL import Image
 from modules.shared import opts, cmd_opts, state
 
-
 class Script(scripts.Script):
     def title(self):
         return "Prompts from file or textbox"
@@ -29,6 +28,9 @@ class Script(scripts.Script):
         checkbox_txt.change(fn=lambda x: [gr.File.update(visible = not x), gr.TextArea.update(visible = x)], inputs=[checkbox_txt], outputs=[file, prompt_txt])
         return [checkbox_txt, file, prompt_txt]
 
+    def on_show(self, checkbox_txt, file, prompt_txt):
+        return [ gr.Checkbox.update(visible = True), gr.File.update(visible = not checkbox_txt), gr.TextArea.update(visible = checkbox_txt) ]
+
     def run(self, p, checkbox_txt, data: bytes, prompt_txt: str):
         if (checkbox_txt):
             lines = [x.strip() for x in prompt_txt.splitlines()]

scripts/xy_grid.py

@@ -10,8 +10,8 @@ import numpy as np
 import modules.scripts as scripts
 import gradio as gr
 
-from modules import images
-from modules.processing import process_images, Processed
+from modules import images, hypernetwork
+from modules.processing import process_images, Processed, get_correct_sampler
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
 import modules.sd_samplers
@@ -56,15 +56,17 @@ def apply_order(p, x, xs):
     p.prompt = prompt_tmp + p.prompt
     
 
-samplers_dict = {}
-for i, sampler in enumerate(modules.sd_samplers.samplers):
-    samplers_dict[sampler.name.lower()] = i
-    for alias in sampler.aliases:
-        samplers_dict[alias.lower()] = i
+def build_samplers_dict(p):
+    samplers_dict = {}
+    for i, sampler in enumerate(get_correct_sampler(p)):
+        samplers_dict[sampler.name.lower()] = i
+        for alias in sampler.aliases:
+            samplers_dict[alias.lower()] = i
+    return samplers_dict
 
 
 def apply_sampler(p, x, xs):
-    sampler_index = samplers_dict.get(x.lower(), None)
+    sampler_index = build_samplers_dict(p).get(x.lower(), None)
     if sampler_index is None:
         raise RuntimeError(f"Unknown sampler: {x}")
 
@@ -78,8 +80,7 @@ def apply_checkpoint(p, x, xs):
 
 
 def apply_hypernetwork(p, x, xs):
-    hn = shared.hypernetworks.get(x, None)
-    opts.data["sd_hypernetwork"] = hn.name if hn is not None else 'None'
+    hypernetwork.load_hypernetwork(x)
 
 
 def format_value_add_label(p, opt, x):
@@ -143,7 +144,7 @@ def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend):
     ver_texts = [[images.GridAnnotation(y)] for y in y_labels]
     hor_texts = [[images.GridAnnotation(x)] for x in x_labels]
 
-    first_pocessed = None
+    first_processed = None
 
     state.job_count = len(xs) * len(ys) * p.n_iter
 
@@ -152,8 +153,8 @@ def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend):
             state.job = f"{ix + iy * len(xs) + 1} out of {len(xs) * len(ys)}"
 
             processed = cell(x, y)
-            if first_pocessed is None:
-                first_pocessed = processed
+            if first_processed is None:
+                first_processed = processed
 
             try:
               res.append(processed.images[0])
@@ -164,9 +165,9 @@ def draw_xy_grid(p, xs, ys, x_labels, y_labels, cell, draw_legend):
     if draw_legend:
         grid = images.draw_grid_annotations(grid, res[0].width, res[0].height, hor_texts, ver_texts)
 
-    first_pocessed.images = [grid]
+    first_processed.images = [grid]
 
-    return first_pocessed
+    return first_processed
 
 
 re_range = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\(([+-]\d+)\s*\))?\s*")
@@ -196,10 +197,10 @@ class Script(scripts.Script):
         return [x_type, x_values, y_type, y_values, draw_legend, no_fixed_seeds]
 
     def run(self, p, x_type, x_values, y_type, y_values, draw_legend, no_fixed_seeds):
-        modules.processing.fix_seed(p)
-        p.batch_size = 1
+        if not no_fixed_seeds:
+            modules.processing.fix_seed(p)
 
-        initial_hn = opts.sd_hypernetwork
+        p.batch_size = 1
 
         def process_axis(opt, vals):
             if opt.label == 'Nothing':
@@ -214,7 +215,6 @@ class Script(scripts.Script):
                     m = re_range.fullmatch(val)
                     mc = re_range_count.fullmatch(val)
                     if m is not None:
-
                         start = int(m.group(1))
                         end = int(m.group(2))+1
                         step = int(m.group(3)) if m.group(3) is not None else 1
@@ -256,6 +256,17 @@ 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")
 
             return valslist
 
@@ -308,6 +319,6 @@ class Script(scripts.Script):
         # restore checkpoint in case it was changed by axes
         modules.sd_models.reload_model_weights(shared.sd_model)
 
-        opts.data["sd_hypernetwork"] = initial_hn
+        hypernetwork.load_hypernetwork(opts.sd_hypernetwork)
 
         return processed

style.css

@@ -103,7 +103,12 @@
 
 #style_apply, #style_create, #interrogate{
     margin: 0.75em 0.25em 0.25em 0.25em;
-    min-width: 3em;
+    min-width: 5em;
+}
+
+#style_apply, #style_create, #deepbooru{
+    margin: 0.75em 0.25em 0.25em 0.25em;
+    min-width: 5em;
 }
 
 #style_pos_col, #style_neg_col{
@@ -393,10 +398,20 @@ input[type="range"]{
 
 #txt2img_interrupt, #img2img_interrupt{
   position: absolute;
-  width: 100%;
+  width: 50%;
   height: 72px;
   background: #b4c0cc;
-  border-radius: 8px;
+  border-radius: 0px;
+  display: none;
+}
+
+#txt2img_skip, #img2img_skip{
+  position: absolute;
+  width: 50%;
+  right: 0px;
+  height: 72px;
+  background: #b4c0cc;
+  border-radius: 0px;
   display: none;
 }
 
@@ -410,4 +425,31 @@ input[type="range"]{
 
 #img2img_image div.h-60{
     height: 480px;
-}
+}
+
+#context-menu{
+    z-index:9999;
+    position:absolute;
+    display:block;
+    padding:0px 0;
+    border:2px solid #a55000;
+    border-radius:8px;
+    box-shadow:1px 1px 2px #CE6400;
+    width: 200px;
+}
+
+.context-menu-items{
+    list-style: none;
+    margin: 0;
+    padding: 0;
+}
+
+.context-menu-items a{
+    display:block;
+    padding:5px;
+    cursor:pointer;
+}
+
+.context-menu-items a:hover{
+    background: #a55000;
+}

webui.py

@@ -60,6 +60,7 @@ def wrap_gradio_gpu_call(func, extra_outputs=None):
         shared.state.current_latent = None
         shared.state.current_image = None
         shared.state.current_image_sampling_step = 0
+        shared.state.skipped = False
         shared.state.interrupted = False
         shared.state.textinfo = None
 
@@ -81,6 +82,9 @@ modules.scripts.load_scripts(os.path.join(script_path, "scripts"))
 shared.sd_model = modules.sd_models.load_model()
 shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights(shared.sd_model)))
 
+loaded_hypernetwork = modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)
+shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
+
 
 def webui():
     # make the program just exit at ctrl+c without waiting for anything