Update ui.py

I had to check the code to work out what splitting was 🤷🏿

README.md

@@ -16,6 +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 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
@@ -61,6 +62,10 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
 - Reloading checkpoints on the fly
 - Checkpoint Merger, a tab that allows you to merge two checkpoints into one
 - [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community
+- [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)
 
 ## 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.

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

@@ -0,0 +1,41 @@
+addEventListener('keydown', (event) => {
+	let target = event.originalTarget || event.composedPath()[0];
+	if (!target.hasAttribute("placeholder")) return;
+	if (!target.placeholder.toLowerCase().includes("prompt")) return;
+
+	let plus = "ArrowUp"
+	let minus = "ArrowDown"
+	if (event.key != plus && event.key != minus) return;
+
+	selectionStart = target.selectionStart;
+	selectionEnd = target.selectionEnd;
+	if(selectionStart == selectionEnd) return;
+
+	event.preventDefault();
+
+	if (selectionStart == 0 || target.value[selectionStart - 1] != "(") {
+		target.value = target.value.slice(0, selectionStart) +
+			"(" + target.value.slice(selectionStart, selectionEnd) + ":1.0)" +
+			target.value.slice(selectionEnd);
+
+		target.focus();
+		target.selectionStart = selectionStart + 1;
+		target.selectionEnd = selectionEnd + 1;
+
+	} else {
+		end = target.value.slice(selectionEnd + 1).indexOf(")") + 1;
+		weight = parseFloat(target.value.slice(selectionEnd + 1, selectionEnd + 1 + end));
+		if (event.key == minus) weight -= 0.1;
+		if (event.key == plus) weight += 0.1;
+
+		weight = parseFloat(weight.toPrecision(12));
+
+		target.value = target.value.slice(0, selectionEnd + 1) +
+			weight +
+			target.value.slice(selectionEnd + 1 + end - 1);
+
+		target.focus();
+		target.selectionStart = selectionStart;
+		target.selectionEnd = selectionEnd;
+	}
+});

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

@@ -86,6 +86,9 @@ 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'

javascript/progressbar.js

@@ -1,11 +1,12 @@
 // 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(progressbar && progressbar.offsetParent){
+    if(opts.show_progress_in_title && progressbar && progressbar.offsetParent){
         if(progressbar.innerText){
             let newtitle = 'Stable Diffusion - ' + progressbar.innerText
             if(document.title != newtitle){
@@ -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

@@ -4,6 +4,7 @@ import os
 import sys
 import importlib.util
 import shlex
+import platform
 
 dir_repos = "repositories"
 dir_tmp = "tmp"
@@ -31,6 +32,7 @@ def extract_arg(args, name):
 
 
 args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test')
+xformers = '--xformers' in args
 
 
 def repo_dir(name):
@@ -89,7 +91,7 @@ def git_clone(url, dir, name, commithash=None):
         if commithash is None:
             return
 
-        current_hash = run(f'"{git}" -C {dir} rev-parse HEAD', None, "Couldn't determine {name}'s hash: {commithash}").strip()
+        current_hash = run(f'"{git}" -C {dir} rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}").strip()
         if current_hash == commithash:
             return
 
@@ -124,6 +126,12 @@ if not is_installed("gfpgan"):
 if not is_installed("clip"):
     run_pip(f"install {clip_package}", "clip")
 
+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")
+
 os.makedirs(dir_repos, exist_ok=True)
 
 git_clone("https://github.com/CompVis/stable-diffusion.git", repo_dir('stable-diffusion'), "Stable Diffusion", stable_diffusion_commit_hash)

modules/esrgan_model.py

@@ -111,7 +111,7 @@ 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

@@ -100,6 +100,8 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v
 
         outputs.append(image)
 
+    devices.torch_gc()
+
     return outputs, plaintext_to_html(info), ''
 
 

modules/hypernetwork.py

@@ -0,0 +1,88 @@
+import glob
+import os
+import sys
+import traceback
+
+import torch
+
+from ldm.util import default
+from modules import devices, shared
+import torch
+from torch import einsum
+from einops import rearrange, repeat
+
+
+class HypernetworkModule(torch.nn.Module):
+    def __init__(self, dim, state_dict):
+        super().__init__()
+
+        self.linear1 = torch.nn.Linear(dim, dim * 2)
+        self.linear2 = torch.nn.Linear(dim * 2, dim)
+
+        self.load_state_dict(state_dict, strict=True)
+        self.to(devices.device)
+
+    def forward(self, x):
+        return x + (self.linear2(self.linear1(x)))
+
+
+class Hypernetwork:
+    filename = None
+    name = None
+
+    def __init__(self, filename):
+        self.filename = filename
+        self.name = os.path.splitext(os.path.basename(filename))[0]
+        self.layers = {}
+
+        state_dict = torch.load(filename, map_location='cpu')
+        for size, sd in state_dict.items():
+            self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
+
+
+def load_hypernetworks(path):
+    res = {}
+
+    for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
+        try:
+            hn = Hypernetwork(filename)
+            res[hn.name] = hn
+        except Exception:
+            print(f"Error loading hypernetwork {filename}", file=sys.stderr)
+            print(traceback.format_exc(), file=sys.stderr)
+
+    return res
+
+
+def attention_CrossAttention_forward(self, x, context=None, mask=None):
+    h = self.heads
+
+    q = self.to_q(x)
+    context = default(context, x)
+
+    hypernetwork = shared.selected_hypernetwork()
+    hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
+
+    if hypernetwork_layers is not None:
+        k = self.to_k(hypernetwork_layers[0](context))
+        v = self.to_v(hypernetwork_layers[1](context))
+    else:
+        k = self.to_k(context)
+        v = self.to_v(context)
+
+    q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
+
+    sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
+
+    if mask is not None:
+        mask = rearrange(mask, 'b ... -> b (...)')
+        max_neg_value = -torch.finfo(sim.dtype).max
+        mask = repeat(mask, 'b j -> (b h) () j', h=h)
+        sim.masked_fill_(~mask, max_neg_value)
+
+    # attention, what we cannot get enough of
+    attn = sim.softmax(dim=-1)
+
+    out = einsum('b i j, b j d -> b i d', attn, v)
+    out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
+    return self.to_out(out)

modules/images.py

@@ -292,18 +292,13 @@ def apply_filename_pattern(x, p, seed, prompt):
         x = x.replace("[cfg]", str(p.cfg_scale))
         x = x.replace("[width]", str(p.width))
         x = x.replace("[height]", str(p.height))
-
-        #currently disabled if using the save button, will work otherwise
-        # if enabled it will cause a bug because styles is not included in the save_files data dictionary
-        if hasattr(p, "styles"):
-            x = x.replace("[styles]", sanitize_filename_part(", ".join([x for x in p.styles if not x == "None"]) or "None", replace_spaces=False))
-
+        x = x.replace("[styles]", sanitize_filename_part(", ".join([x for x in p.styles if not x == "None"]) or "None", replace_spaces=False))
         x = x.replace("[sampler]", sanitize_filename_part(sd_samplers.samplers[p.sampler_index].name, replace_spaces=False))
 
-    x = x.replace("[model_hash]", shared.sd_model.sd_model_hash)
+    x = x.replace("[model_hash]", getattr(p, "sd_model_hash", shared.sd_model.sd_model_hash))
     x = x.replace("[date]", datetime.date.today().isoformat())
     x = x.replace("[datetime]", datetime.datetime.now().strftime("%Y%m%d%H%M%S"))
-    x = x.replace("[job_timestamp]", shared.state.job_timestamp)
+    x = x.replace("[job_timestamp]", getattr(p, "job_timestamp", shared.state.job_timestamp))
 
     # Apply [prompt] at last. Because it may contain any replacement word.^M
     if prompt is not None:
@@ -353,7 +348,7 @@ def get_next_sequence_number(path, basename):
     return result + 1
 
 
-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=""):
+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):
     if short_filename or prompt is None or seed is None:
         file_decoration = ""
     elif opts.save_to_dirs:
@@ -377,7 +372,8 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     else:
         pnginfo = None
 
-    save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt)
+    if save_to_dirs is None:
+        save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt)
 
     if save_to_dirs:
         dirname = apply_filename_pattern(opts.directories_filename_pattern or "[prompt_words]", p, seed, prompt).strip('\\ /')
@@ -431,4 +427,4 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
         with open(f"{fullfn_without_extension}.txt", "w", encoding="utf8") as file:
             file.write(info + "\n")
 
-
+    return 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/processing.py

@@ -11,7 +11,7 @@ import cv2
 from skimage import exposure
 
 import modules.sd_hijack
-from modules import devices, prompt_parser, masking, sd_samplers
+from modules import devices, prompt_parser, masking, sd_samplers, lowvram
 from modules.sd_hijack import model_hijack
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
@@ -121,6 +121,8 @@ class Processed:
         self.denoising_strength = getattr(p, 'denoising_strength', None)
         self.extra_generation_params = p.extra_generation_params
         self.index_of_first_image = index_of_first_image
+        self.styles = p.styles
+        self.job_timestamp = state.job_timestamp
 
         self.eta = p.eta
         self.ddim_discretize = p.ddim_discretize
@@ -139,6 +141,7 @@ class Processed:
         self.all_subseeds = all_subseeds or [self.subseed]
         self.infotexts = infotexts or [info]
 
+
     def js(self):
         obj = {
             "prompt": self.prompt,
@@ -165,6 +168,8 @@ class Processed:
             "extra_generation_params": self.extra_generation_params,
             "index_of_first_image": self.index_of_first_image,
             "infotexts": self.infotexts,
+            "styles": self.styles,
+            "job_timestamp": self.job_timestamp,
         }
 
         return json.dumps(obj)
@@ -308,6 +313,7 @@ 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 = {}
 
@@ -345,6 +351,9 @@ 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
 
@@ -371,7 +380,7 @@ 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
                 # use the image collected previously in sampler loop
@@ -382,6 +391,13 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             x_samples_ddim = p.sd_model.decode_first_stage(samples_ddim)
             x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
 
+            del samples_ddim
+
+            if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
+                lowvram.send_everything_to_cpu()
+
+            devices.torch_gc()
+
             if opts.filter_nsfw:
                 import modules.safety as safety
                 x_samples_ddim = modules.safety.censor_batch(x_samples_ddim)
@@ -423,9 +439,15 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
                 if opts.samples_save and not p.do_not_save_samples:
                     images.save_image(image, p.outpath_samples, "", seeds[i], prompts[i], opts.samples_format, info=infotext(n, i), p=p)
 
-                infotexts.append(infotext(n, i))
+                text = infotext(n, i)
+                infotexts.append(text)
+                image.info["parameters"] = text
                 output_images.append(image)
 
+            del x_samples_ddim 
+
+            devices.torch_gc()
+
             state.nextjob()
 
         p.color_corrections = None
@@ -436,7 +458,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             grid = images.image_grid(output_images, p.batch_size)
 
             if opts.return_grid:
-                infotexts.insert(0, infotext())
+                text = infotext()
+                infotexts.insert(0, text)
+                grid.info["parameters"] = text
                 output_images.insert(0, grid)
                 index_of_first_image = 1
 
@@ -663,4 +687,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         if self.mask is not None:
             samples = samples * self.nmask + self.init_latent * self.mask
 
+        del x
+        devices.torch_gc()
+
         return samples

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/sd_hijack.py

@@ -5,9 +5,10 @@ import traceback
 import torch
 import numpy as np
 from torch import einsum
+from torch.nn.functional import silu
 
 import modules.textual_inversion.textual_inversion
-from modules import prompt_parser, devices, sd_hijack_optimizations, shared
+from modules import prompt_parser, devices, sd_hijack_optimizations, shared, hypernetwork
 from modules.shared import opts, device, cmd_opts
 
 import ldm.modules.attention
@@ -17,22 +18,37 @@ 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():
-    if cmd_opts.opt_split_attention_v1:
+    undo_optimizations()
+
+    ldm.modules.diffusionmodules.model.nonlinearity = silu
+
+    if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and torch.cuda.get_device_capability(shared.device) == (8, 6)):
+        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.nonlinearity = sd_hijack_optimizations.nonlinearity_hijack
         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
 
 
 def undo_optimizations():
-    ldm.modules.attention.CrossAttention.forward = attention_CrossAttention_forward
+    ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
     ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity
     ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
 
 
+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 = []
@@ -78,10 +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):
@@ -90,7 +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]
@@ -112,7 +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)
@@ -144,19 +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
 
@@ -173,7 +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)
 
@@ -187,7 +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 = []
@@ -259,17 +269,24 @@ 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)
+        target_token_count = get_target_prompt_token_count(token_count) + 2
+
+        position_ids_array = [min(x, 75) for x in range(target_token_count-1)] + [76]
+        position_ids = torch.asarray(position_ids_array, device=devices.device).expand((1, -1))
+
+        remade_batch_tokens_of_same_length = [x + [self.wrapped.tokenizer.eos_token_id] * (target_token_count - len(x)) for x in remade_batch_tokens]
+        tokens = torch.asarray(remade_batch_tokens_of_same_length).to(device)
+        outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids)
         z = outputs.last_hidden_state
 
         # restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
-        batch_multipliers = 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

@@ -1,22 +1,46 @@
 import math
+import sys
+import traceback
+
 import torch
 from torch import einsum
 
 from ldm.util import default
 from einops import rearrange
 
+from modules import shared
+
+if shared.cmd_opts.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.selected_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):
@@ -29,6 +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
@@ -42,8 +67,19 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
 
     q_in = self.to_q(x)
     context = default(context, x)
-    k_in = self.to_k(context) * self.scale
-    v_in = self.to_v(context)
+
+    hypernetwork = shared.selected_hypernetwork()
+    hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
+
+    if hypernetwork_layers is not None:
+        k_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)
+
+    k_in *= self.scale
+
     del context, x
 
     q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in))
@@ -92,13 +128,24 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
 
     return self.to_out(r2)
 
-def nonlinearity_hijack(x):
-    # swish
-    t = torch.sigmoid(x)
-    x *= t
-    del t
+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.selected_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)
 
-    return x
+    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
@@ -162,3 +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

@@ -122,7 +122,11 @@ def load_model_weights(model, checkpoint_file, sd_model_hash):
     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"]
+    
+    if "state_dict" in pl_sd:
+        sd = pl_sd["state_dict"]
+    else:
+        sd = pl_sd
 
     model.load_state_dict(sd, strict=False)
 
@@ -134,6 +138,14 @@ def load_model_weights(model, checkpoint_file, sd_model_hash):
 
     devices.dtype = torch.float32 if shared.cmd_opts.no_half else torch.float16
 
+    vae_file = os.path.splitext(checkpoint_file)[0] + ".vae.pt"
+    if os.path.exists(vae_file):
+        print(f"Loading VAE weights from: {vae_file}")
+        vae_ckpt = torch.load(vae_file, map_location="cpu")
+        vae_dict = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss"}
+
+        model.first_stage_model.load_state_dict(vae_dict)
+
     model.sd_model_hash = sd_model_hash
     model.sd_model_checkpint = checkpoint_file
 

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
@@ -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:
@@ -338,9 +359,11 @@ class KDiffusionSampler:
         steps, t_enc = setup_img2img_steps(p, steps)
 
         if p.sampler_noise_scheduler_override:
-          sigmas = p.sampler_noise_scheduler_override(steps)
+            sigmas = p.sampler_noise_scheduler_override(steps)
+        elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
+            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=0.1, sigma_max=10, device=shared.device)
         else:
-          sigmas = self.model_wrap.get_sigmas(steps)
+            sigmas = self.model_wrap.get_sigmas(steps)
 
         noise = noise * sigmas[steps - t_enc - 1]
         xi = x + noise

modules/shared.py

@@ -13,12 +13,11 @@ import modules.memmon
 import modules.sd_models
 import modules.styles
 import modules.devices as devices
-from modules import sd_samplers
-from modules.paths import script_path, sd_path
+from modules import sd_samplers, hypernetwork
+from modules.paths import models_path, script_path, sd_path
 
 sd_model_file = os.path.join(script_path, 'model.ckpt')
 default_sd_model_file = sd_model_file
-model_path = os.path.join(script_path, 'models')
 parser = argparse.ArgumentParser()
 parser.add_argument("--config", type=str, default=os.path.join(sd_path, "configs/stable-diffusion/v1-inference.yaml"), help="path to config which constructs model",)
 parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
@@ -36,14 +35,16 @@ parser.add_argument("--always-batch-cond-uncond", action='store_true', help="dis
 parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
 parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
 parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)")
-parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(model_path, 'Codeformer'))
-parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(model_path, 'GFPGAN'))
-parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(model_path, 'ESRGAN'))
-parser.add_argument("--bsrgan-models-path", type=str, help="Path to directory with BSRGAN model file(s).", default=os.path.join(model_path, 'BSRGAN'))
-parser.add_argument("--realesrgan-models-path", type=str, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(model_path, 'RealESRGAN'))
-parser.add_argument("--scunet-models-path", type=str, help="Path to directory with ScuNET model file(s).", default=os.path.join(model_path, 'ScuNET'))
-parser.add_argument("--swinir-models-path", type=str, help="Path to directory with SwinIR model file(s).", default=os.path.join(model_path, 'SwinIR'))
-parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with LDSR model file(s).", default=os.path.join(model_path, 'LDSR'))
+parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
+parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
+parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
+parser.add_argument("--bsrgan-models-path", type=str, help="Path to directory with BSRGAN model file(s).", default=os.path.join(models_path, 'BSRGAN'))
+parser.add_argument("--realesrgan-models-path", type=str, help="Path to directory with RealESRGAN model file(s).", default=os.path.join(models_path, 'RealESRGAN'))
+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("--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")
@@ -74,11 +75,18 @@ 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)
+
 
 class State:
+    skipped = False
     interrupted = False
     job = ""
     job_no = 0
@@ -91,6 +99,9 @@ class State:
     current_image_sampling_step = 0
     textinfo = None
 
+    def skip(self):
+        self.skipped = True
+
     def interrupt(self):
         self.interrupted = True
 
@@ -113,8 +124,6 @@ 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():
@@ -207,6 +216,7 @@ options_templates.update(options_section(('system', "System"), {
 
 options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}),
+    "sd_hypernetwork": OptionInfo("None", "Stable Diffusion finetune hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}),
     "img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),
     "save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"),
     "img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."),
@@ -236,6 +246,7 @@ options_templates.update(options_section(('ui', "User interface"), {
     "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"),
+    "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
 }))
 
 options_templates.update(options_section(('sampler-params', "Sampler parameters"), {

modules/ui.py

@@ -35,7 +35,7 @@ import modules.codeformer_model
 import modules.styles
 import modules.generation_parameters_copypaste
 from modules import prompt_parser
-from modules.images import apply_filename_pattern, get_next_sequence_number
+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
@@ -114,20 +114,13 @@ def save_files(js_data, images, index):
     p = MyObject(data)
     path = opts.outdir_save
     save_to_dirs = opts.use_save_to_dirs_for_ui
-
-    if save_to_dirs:
-        dirname = apply_filename_pattern(opts.directories_filename_pattern or "[prompt_words]", p, p.seed, p.prompt)
-        path = os.path.join(opts.outdir_save, dirname)
-
-    os.makedirs(path, exist_ok=True)
-  
+    extension: str = opts.samples_format
+    start_index = 0
 
     if index > -1 and opts.save_selected_only and (index >= data["index_of_first_image"]):  # ensures we are looking at a specific non-grid picture, and we have save_selected_only
 
         images = [images[index]]
-        infotexts = [data["infotexts"][index]]
-    else:
-        infotexts = data["infotexts"]
+        start_index = index
 
     with open(os.path.join(opts.outdir_save, "log.csv"), "a", encoding="utf8", newline='') as file:
         at_start = file.tell() == 0
@@ -135,37 +128,18 @@ def save_files(js_data, images, index):
         if at_start:
             writer.writerow(["prompt", "seed", "width", "height", "sampler", "cfgs", "steps", "filename", "negative_prompt"])
 
-        file_decoration = opts.samples_filename_pattern or "[seed]-[prompt_spaces]"
-        if file_decoration != "":
-            file_decoration = "-" + file_decoration.lower()
-        file_decoration = apply_filename_pattern(file_decoration, p, p.seed, p.prompt)
-        truncated = (file_decoration[:240] + '..') if len(file_decoration) > 240 else file_decoration
-        filename_base = truncated
-        extension = opts.samples_format.lower()
-
-        basecount = get_next_sequence_number(path, "")
-        for i, filedata in enumerate(images):
-            file_number = f"{basecount+i:05}"
-            filename = file_number + filename_base + f".{extension}"
-            filepath = os.path.join(path, filename)
-
-
+        for image_index, filedata in enumerate(images, start_index):
             if filedata.startswith("data:image/png;base64,"):
                 filedata = filedata[len("data:image/png;base64,"):]
 
             image = Image.open(io.BytesIO(base64.decodebytes(filedata.encode('utf-8'))))
-            if opts.enable_pnginfo and extension == 'png':
-                pnginfo = PngImagePlugin.PngInfo()
-                pnginfo.add_text('parameters', infotexts[i])
-                image.save(filepath, pnginfo=pnginfo)
-            else:
-                image.save(filepath, quality=opts.jpeg_quality)
 
-            if opts.enable_pnginfo and extension in ("jpg", "jpeg", "webp"):
-                piexif.insert(piexif.dump({"Exif": {
-                    piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(infotexts[i], encoding="unicode")
-                }}), filepath)
+            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)
+
+            filename = os.path.relpath(fullfn, path)
             filenames.append(filename)
 
         writer.writerow([data["prompt"], data["seed"], data["width"], data["height"], data["sampler"], data["cfg_scale"], data["steps"], filenames[0], data["negative_prompt"]])
@@ -217,6 +191,7 @@ 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
 
@@ -437,9 +412,16 @@ 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=[],
@@ -964,7 +946,7 @@ 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'):
@@ -998,9 +980,9 @@ 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):

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/xy_grid.py

@@ -1,8 +1,9 @@
 from collections import namedtuple
 from copy import copy
-from itertools import permutations
+from itertools import permutations, chain
 import random
-
+import csv
+from io import StringIO
 from PIL import Image
 import numpy as np
 
@@ -76,6 +77,11 @@ def apply_checkpoint(p, x, xs):
     modules.sd_models.reload_model_weights(shared.sd_model, info)
 
 
+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'
+
+
 def format_value_add_label(p, opt, x):
     if type(x) == float:
         x = round(x, 8)
@@ -121,6 +127,7 @@ axis_options = [
     AxisOption("Prompt order", str_permutations, apply_order, format_value_join_list),
     AxisOption("Sampler", str, apply_sampler, format_value),
     AxisOption("Checkpoint name", str, apply_checkpoint, format_value),
+    AxisOption("Hypernetwork", str, apply_hypernetwork, format_value),
     AxisOption("Sigma Churn", float, apply_field("s_churn"), format_value_add_label),
     AxisOption("Sigma min", float, apply_field("s_tmin"), format_value_add_label),
     AxisOption("Sigma max", float, apply_field("s_tmax"), format_value_add_label),
@@ -168,7 +175,6 @@ re_range_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d
 re_range_count = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\[(\d+)\s*\])?\s*")
 re_range_count_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d*)?)(?:\s*\[(\d+(?:.\d*)?)\s*\])?\s*")
 
-
 class Script(scripts.Script):
     def title(self):
         return "X/Y plot"
@@ -193,11 +199,13 @@ class Script(scripts.Script):
         modules.processing.fix_seed(p)
         p.batch_size = 1
 
+        initial_hn = opts.sd_hypernetwork
+
         def process_axis(opt, vals):
             if opt.label == 'Nothing':
                 return [0]
 
-            valslist = [x.strip() for x in vals.split(",")]
+            valslist = [x.strip() for x in chain.from_iterable(csv.reader(StringIO(vals)))]
 
             if opt.type == int:
                 valslist_ext = []
@@ -300,4 +308,6 @@ 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
+
         return processed

style.css

@@ -393,10 +393,20 @@ 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;
 }
 
@@ -404,6 +414,37 @@ input[type="range"]{
 	color: red;
 }
 
+.gallery-item {
+    --tw-bg-opacity: 0 !important;
+}
+
 #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

@@ -5,6 +5,8 @@ import importlib
 import signal
 import threading
 
+from fastapi.middleware.gzip import GZipMiddleware
+
 from modules.paths import script_path
 
 from modules import devices, sd_samplers
@@ -58,6 +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
 
@@ -92,7 +95,7 @@ def webui():
 
         demo = modules.ui.create_ui(wrap_gradio_gpu_call=wrap_gradio_gpu_call)
         
-        demo.launch(
+        app,local_url,share_url = demo.launch(
             share=cmd_opts.share,
             server_name="0.0.0.0" if cmd_opts.listen else None,
             server_port=cmd_opts.port,
@@ -101,6 +104,8 @@ def webui():
             inbrowser=cmd_opts.autolaunch,
             prevent_thread_lock=True
         )
+        
+        app.add_middleware(GZipMiddleware,minimum_size=1000)
 
         while 1:
             time.sleep(0.5)