Merge branch 'dev' into test-fp8

javascript/edit-attention.js

@@ -19,17 +19,28 @@ function keyupEditAttention(event) {
         let beforeParen = before.lastIndexOf(OPEN);
         if (beforeParen == -1) return false;
 
+        let beforeClosingParen = before.lastIndexOf(CLOSE);
+        if (beforeClosingParen != -1 && beforeClosingParen > beforeParen) return false;
+
         // Find closing parenthesis around current cursor
         const after = text.substring(selectionStart);
         let afterParen = after.indexOf(CLOSE);
         if (afterParen == -1) return false;
 
+        let afterOpeningParen = after.indexOf(OPEN);
+        if (afterOpeningParen != -1 && afterOpeningParen < afterParen) return false;
+
         // Set the selection to the text between the parenthesis
         const parenContent = text.substring(beforeParen + 1, selectionStart + afterParen);
-        if (!/.*:-?[\d.]+/s.test(parenContent)) return false;
+        if (/.*:-?[\d.]+/s.test(parenContent)) {
             const lastColon = parenContent.lastIndexOf(":");
             selectionStart = beforeParen + 1;
             selectionEnd = selectionStart + lastColon;
+        } else {
+            selectionStart = beforeParen + 1;
+            selectionEnd = selectionStart + parenContent.length;
+        }
+
         target.setSelectionRange(selectionStart, selectionEnd);
         return true;
     }
@@ -58,7 +69,7 @@ function keyupEditAttention(event) {
     }
 
     // If the user hasn't selected anything, let's select their current parenthesis block or word
-    if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')')) {
+    if (!selectCurrentParenthesisBlock('<', '>') && !selectCurrentParenthesisBlock('(', ')') && !selectCurrentParenthesisBlock('[', ']')) {
         selectCurrentWord();
     }
 
@@ -66,24 +77,23 @@ function keyupEditAttention(event) {
 
     var closeCharacter = ')';
     var delta = opts.keyedit_precision_attention;
+    var start = selectionStart > 0 ? text[selectionStart - 1] : "";
+    var end = text[selectionEnd];
 
-    if (selectionStart > 0 && /<.*:-?[\d.]+>/s.test(text.slice(selectionStart - 1, selectionEnd + text.slice(selectionEnd).indexOf(">") + 1))) {
+    if (start == '<') {
         closeCharacter = '>';
         delta = opts.keyedit_precision_extra;
-    } else if (selectionStart > 0 && /\(.*\)|\[.*\]/s.test(text.slice(selectionStart - 1, selectionEnd + 1))) {
-        let start = text[selectionStart - 1];
-        let end = text[selectionEnd];
-        if (opts.keyedit_convert) {
+    } else if (start == '(' && end == ')' || start == '[' && end == ']') { // convert old-style (((emphasis)))
         let numParen = 0;
 
         while (text[selectionStart - numParen - 1] == start && text[selectionEnd + numParen] == end) {
             numParen++;
         }
 
-            if (start == "(") {
-                weight = 1.1 ** numParen;
-            } else {
+        if (start == "[") {
             weight = (1 / 1.1) ** numParen;
+        } else {
+            weight = 1.1 ** numParen;
         }
 
         weight = Math.round(weight / opts.keyedit_precision_attention) * opts.keyedit_precision_attention;
@@ -91,19 +101,7 @@ function keyupEditAttention(event) {
         text = text.slice(0, selectionStart - numParen) + "(" + text.slice(selectionStart, selectionEnd) + ":" + weight + ")" + text.slice(selectionEnd + numParen);
         selectionStart -= numParen - 1;
         selectionEnd -= numParen - 1;
-        } else {
-            closeCharacter = null;
-            if (isPlus) {
-                text = text.slice(0, selectionStart) + start + text.slice(selectionStart, selectionEnd) + end + text.slice(selectionEnd);
-                selectionStart++;
-                selectionEnd++;
-            } else {
-                text = text.slice(0, selectionStart - 1) + text.slice(selectionStart, selectionEnd) + text.slice(selectionEnd + 1);
-                selectionStart--;
-                selectionEnd--;
-            }
-        }
-    } else if (selectionStart == 0 || !/\(.*:-?[\d.]+\)/s.test(text.slice(selectionStart - 1, selectionEnd + text.slice(selectionEnd).indexOf(")") + 1))) {
+    } else if (start != '(') {
         // do not include spaces at the end
         while (selectionEnd > selectionStart && text[selectionEnd - 1] == ' ') {
             selectionEnd--;
@@ -119,9 +117,9 @@ function keyupEditAttention(event) {
         selectionEnd++;
     }
 
-    if (closeCharacter) {
-        var end = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
-        var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + end));
+    if (text[selectionEnd] != ':') return;
+    var weightLength = text.slice(selectionEnd + 1).indexOf(closeCharacter) + 1;
+    var weight = parseFloat(text.slice(selectionEnd + 1, selectionEnd + weightLength));
     if (isNaN(weight)) return;
 
     weight += isPlus ? delta : -delta;
@@ -134,8 +132,7 @@ function keyupEditAttention(event) {
         selectionStart--;
         selectionEnd--;
     } else {
-            text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + end);
-        }
+        text = text.slice(0, selectionEnd + 1) + weight + text.slice(selectionEnd + weightLength);
     }
 
     target.focus();

modules/gfpgan_model.py

@@ -9,6 +9,7 @@ from modules import paths, shared, devices, modelloader, errors
 model_dir = "GFPGAN"
 user_path = None
 model_path = os.path.join(paths.models_path, model_dir)
+model_file_path = None
 model_url = "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth"
 have_gfpgan = False
 loaded_gfpgan_model = None
@@ -17,6 +18,7 @@ loaded_gfpgan_model = None
 def gfpgann():
     global loaded_gfpgan_model
     global model_path
+    global model_file_path
     if loaded_gfpgan_model is not None:
         loaded_gfpgan_model.gfpgan.to(devices.device_gfpgan)
         return loaded_gfpgan_model
@@ -24,17 +26,24 @@ def gfpgann():
     if gfpgan_constructor is None:
         return None
 
-    models = modelloader.load_models(model_path, model_url, user_path, ext_filter="GFPGAN")
+    models = modelloader.load_models(model_path, model_url, user_path, ext_filter=['.pth'])
+
     if len(models) == 1 and models[0].startswith("http"):
         model_file = models[0]
     elif len(models) != 0:
-        latest_file = max(models, key=os.path.getctime)
+        gfp_models = []
+        for item in models:
+            if 'GFPGAN' in os.path.basename(item):
+                gfp_models.append(item)
+        latest_file = max(gfp_models, key=os.path.getctime)
         model_file = latest_file
     else:
         print("Unable to load gfpgan model!")
         return None
+
     if hasattr(facexlib.detection.retinaface, 'device'):
         facexlib.detection.retinaface.device = devices.device_gfpgan
+    model_file_path = model_file
     model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=devices.device_gfpgan)
     loaded_gfpgan_model = model
 
@@ -77,19 +86,25 @@ def setup_model(dirname):
         global user_path
         global have_gfpgan
         global gfpgan_constructor
+        global model_file_path
+
+        facexlib_path = model_path
+
+        if dirname is not None:
+            facexlib_path = dirname
 
         load_file_from_url_orig = gfpgan.utils.load_file_from_url
         facex_load_file_from_url_orig = facexlib.detection.load_file_from_url
         facex_load_file_from_url_orig2 = facexlib.parsing.load_file_from_url
 
         def my_load_file_from_url(**kwargs):
-            return load_file_from_url_orig(**dict(kwargs, model_dir=model_path))
+            return load_file_from_url_orig(**dict(kwargs, model_dir=model_file_path))
 
         def facex_load_file_from_url(**kwargs):
-            return facex_load_file_from_url_orig(**dict(kwargs, save_dir=model_path, model_dir=None))
+            return facex_load_file_from_url_orig(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
 
         def facex_load_file_from_url2(**kwargs):
-            return facex_load_file_from_url_orig2(**dict(kwargs, save_dir=model_path, model_dir=None))
+            return facex_load_file_from_url_orig2(**dict(kwargs, save_dir=facexlib_path, model_dir=None))
 
         gfpgan.utils.load_file_from_url = my_load_file_from_url
         facexlib.detection.load_file_from_url = facex_load_file_from_url

modules/processing.py

@@ -886,6 +886,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
             devices.torch_gc()
 
+            state.nextjob()
+
             if p.scripts is not None:
                 p.scripts.postprocess_batch(p, x_samples_ddim, batch_number=n)
 
@@ -958,8 +960,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
             devices.torch_gc()
 
-            state.nextjob()
-
         if not infotexts:
             infotexts.append(Processed(p, []).infotext(p, 0))
 

modules/prompt_parser.py

@@ -4,7 +4,7 @@ import re
 from collections import namedtuple
 import lark
 
-# a prompt like this: "fantasy landscape with a [mountain:lake:0.25] and [an oak:a christmas tree:0.75][ in foreground::0.6][ in background:0.25] [shoddy:masterful:0.5]"
+# a prompt like this: "fantasy landscape with a [mountain:lake:0.25] and [an oak:a christmas tree:0.75][ in foreground::0.6][: in background:0.25] [shoddy:masterful:0.5]"
 # will be represented with prompt_schedule like this (assuming steps=100):
 # [25, 'fantasy landscape with a mountain and an oak in foreground shoddy']
 # [50, 'fantasy landscape with a lake and an oak in foreground in background shoddy']

modules/shared_options.py

@@ -259,9 +259,8 @@ options_templates.update(options_section(('ui', "User interface"), {
     "dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row").needs_reload_ui(),
     "keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
     "keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing <extra networks:0.9>", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
-    "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~()[]<>| ", "Ctrl+up/down word delimiters"),
+    "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~() ", "Ctrl+up/down word delimiters"),
     "keyedit_delimiters_whitespace": OptionInfo(["Tab", "Carriage Return", "Line Feed"], "Ctrl+up/down whitespace delimiters", gr.CheckboxGroup, lambda: {"choices": ["Tab", "Carriage Return", "Line Feed"]}),
-    "keyedit_convert": OptionInfo(True, "Convert (attention) to (attention:1.1)"),
     "keyedit_move": OptionInfo(True, "Alt+left/right moves prompt elements"),
     "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_reload_ui(),
     "ui_tab_order": OptionInfo([], "UI tab order", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),

requirements_versions.txt

@@ -29,3 +29,4 @@ torch
 torchdiffeq==0.2.3
 torchsde==0.2.6
 transformers==4.30.2
+httpx==0.24.1

scripts/prompts_from_file.py

@@ -114,6 +114,7 @@ class Script(scripts.Script):
     def ui(self, is_img2img):
         checkbox_iterate = gr.Checkbox(label="Iterate seed every line", value=False, elem_id=self.elem_id("checkbox_iterate"))
         checkbox_iterate_batch = gr.Checkbox(label="Use same random seed for all lines", value=False, elem_id=self.elem_id("checkbox_iterate_batch"))
+        prompt_position = gr.Radio(["start", "end"], label="Insert prompts at the", elem_id=self.elem_id("prompt_position"), value="start")
 
         prompt_txt = gr.Textbox(label="List of prompt inputs", lines=1, elem_id=self.elem_id("prompt_txt"))
         file = gr.File(label="Upload prompt inputs", type='binary', elem_id=self.elem_id("file"))
@@ -124,9 +125,9 @@ class Script(scripts.Script):
         # We don't shrink back to 1, because that causes the control to ignore [enter], and it may
         # be unclear to the user that shift-enter is needed.
         prompt_txt.change(lambda tb: gr.update(lines=7) if ("\n" in tb) else gr.update(lines=2), inputs=[prompt_txt], outputs=[prompt_txt], show_progress=False)
-        return [checkbox_iterate, checkbox_iterate_batch, prompt_txt]
+        return [checkbox_iterate, checkbox_iterate_batch, prompt_position, prompt_txt]
 
-    def run(self, p, checkbox_iterate, checkbox_iterate_batch, prompt_txt: str):
+    def run(self, p, checkbox_iterate, checkbox_iterate_batch, prompt_position, prompt_txt: str):
         lines = [x for x in (x.strip() for x in prompt_txt.splitlines()) if x]
 
         p.do_not_save_grid = True
@@ -167,6 +168,18 @@ class Script(scripts.Script):
                 else:
                     setattr(copy_p, k, v)
 
+            if args.get("prompt") and p.prompt:
+                if prompt_position == "start":
+                    copy_p.prompt = args.get("prompt") + " " + p.prompt
+                else:
+                    copy_p.prompt = p.prompt + " " + args.get("prompt")
+
+            if args.get("negative_prompt") and p.negative_prompt:
+                if prompt_position == "start":
+                    copy_p.negative_prompt = args.get("negative_prompt") + " " + p.negative_prompt
+                else:
+                    copy_p.negative_prompt = p.negative_prompt + " " + args.get("negative_prompt")
+
             proc = process_images(copy_p)
             images += proc.images