feat: add checkbox and config to disable updating selected styles whe…

…n describing an image (#3430)

* feat: add checkbox and config to disable updating selected styles when describing an image

* i18n: add translation for checkbox label

* feat: change describe content type from Radio to CheckboxGroup, add config

* fix: cast set to list when styles contains elements

* feat: sort styles after describe

language/en.json

@@ -17,6 +17,7 @@
     "Content Type": "Content Type",
     "Photograph": "Photograph",
     "Art/Anime": "Art/Anime",
+    "Appy Styles": "Appy Styles",
     "Describe this Image into Prompt": "Describe this Image into Prompt",
     "Image Size and Recommended Size": "Image Size and Recommended Size",
     "Upscale or Variation:": "Upscale or Variation:",

modules/config.py

@@ -702,6 +702,19 @@ def init_temp_path(path: str | None, default_path: str) -> str:
     expected_type=str
 )
 
+default_describe_apply_prompts_checkbox = get_config_item_or_set_default(
+    key='default_describe_apply_prompts_checkbox',
+    default_value=True,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
+default_describe_content_type = get_config_item_or_set_default(
+    key='default_describe_content_type',
+    default_value=[modules.flags.describe_type_photo],
+    validator=lambda x: all(k in modules.flags.describe_types for k in x),
+    expected_type=list
+)
+
 config_dict["default_loras"] = default_loras = default_loras[:default_max_lora_number] + [[True, 'None', 1.0] for _ in range(default_max_lora_number - len(default_loras))]
 
 # mapping config to meta parameter

modules/flags.py

@@ -96,6 +96,7 @@
 
 describe_type_photo = 'Photograph'
 describe_type_anime = 'Art/Anime'
+describe_types = [describe_type_photo, describe_type_anime]
 
 sdxl_aspect_ratios = [
     '704*1408', '704*1344', '768*1344', '768*1280', '832*1216', '832*1152',

webui.py

@@ -337,10 +337,11 @@ def generate_mask(image, mask_model, cloth_category, dino_prompt_text, sam_model
                             with gr.Column():
                                 describe_input_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False)
                             with gr.Column():
-                                describe_method = gr.Radio(
+                                describe_methods = gr.CheckboxGroup(
                                     label='Content Type',
-                                    choices=[flags.describe_type_photo, flags.describe_type_anime],
-                                    value=flags.describe_type_photo)
+                                    choices=flags.describe_types,
+                                    value=modules.config.default_describe_content_type)
+                                describe_apply_styles = gr.Checkbox(label='Appy Styles', value=modules.config.default_describe_apply_prompts_checkbox)
                                 describe_btn = gr.Button(value='Describe this Image into Prompt')
                                 describe_image_size = gr.Textbox(label='Image Size and Recommended Size', elem_id='describe_image_size', visible=False)
                                 gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/1363" target="_blank">\U0001F4D4 Documentation</a>')
@@ -1060,30 +1061,54 @@ def trigger_metadata_import(file, state_is_generating):
                 gr.Audio(interactive=False, value=notification_file, elem_id='audio_notification', visible=False)
                 break
 
-        def trigger_describe(mode, img):
-            if mode == flags.describe_type_photo:
+        def trigger_describe(modes, img, apply_styles):
+            describe_prompts = []
+            styles = set()
+
+            if flags.describe_type_photo in modes:
                 from extras.interrogate import default_interrogator as default_interrogator_photo
-                return default_interrogator_photo(img), ["Fooocus V2", "Fooocus Enhance", "Fooocus Sharp"]
-            if mode == flags.describe_type_anime:
+                describe_prompts.append(default_interrogator_photo(img))
+                styles.update(["Fooocus V2", "Fooocus Enhance", "Fooocus Sharp"])
+
+            if flags.describe_type_anime in modes:
                 from extras.wd14tagger import default_interrogator as default_interrogator_anime
-                return default_interrogator_anime(img), ["Fooocus V2", "Fooocus Masterpiece"]
-            return mode, ["Fooocus V2"]
+                describe_prompts.append(default_interrogator_anime(img))
+                styles.update(["Fooocus V2", "Fooocus Masterpiece"])
 
-        describe_btn.click(trigger_describe, inputs=[describe_method, describe_input_image],
-                           outputs=[prompt, style_selections], show_progress=True, queue=True)
+            if len(styles) == 0 or not apply_styles:
+                styles = gr.update()
+            else:
+                styles = list(styles)
+
+            if len(describe_prompts) == 0:
+                describe_prompt = gr.update()
+            else:
+                describe_prompt = ', '.join(describe_prompts)
+
+            return describe_prompt, styles
+
+        describe_btn.click(trigger_describe, inputs=[describe_methods, describe_input_image, describe_apply_styles],
+                           outputs=[prompt, style_selections], show_progress=True, queue=True) \
+            .then(fn=style_sorter.sort_styles, inputs=style_selections, outputs=style_selections, queue=False, show_progress=False) \
+            .then(lambda: None, _js='()=>{refresh_style_localization();}')
 
         if args_manager.args.enable_auto_describe_image:
-            def trigger_auto_describe(mode, img, prompt):
+            def trigger_auto_describe(mode, img, prompt, apply_styles):
                 # keep prompt if not empty
                 if prompt == '':
-                    return trigger_describe(mode, img)
+                    return trigger_describe(mode, img, apply_styles)
                 return gr.update(), gr.update()
 
-            uov_input_image.upload(trigger_auto_describe, inputs=[describe_method, uov_input_image, prompt],
-                                   outputs=[prompt, style_selections], show_progress=True, queue=True)
+            uov_input_image.upload(trigger_auto_describe, inputs=[describe_methods, uov_input_image, prompt, describe_apply_styles],
+                                   outputs=[prompt, style_selections], show_progress=True, queue=True) \
+                .then(fn=style_sorter.sort_styles, inputs=style_selections, outputs=style_selections, queue=False, show_progress=False) \
+                .then(lambda: None, _js='()=>{refresh_style_localization();}')
 
             enhance_input_image.upload(lambda: gr.update(value=True), outputs=enhance_checkbox, queue=False, show_progress=False) \
-                .then(trigger_auto_describe, inputs=[describe_method, enhance_input_image, prompt], outputs=[prompt, style_selections], show_progress=True, queue=True)
+                .then(trigger_auto_describe, inputs=[describe_methods, enhance_input_image, prompt, describe_apply_styles],
+                      outputs=[prompt, style_selections], show_progress=True, queue=True) \
+                .then(fn=style_sorter.sort_styles, inputs=style_selections, outputs=style_selections, queue=False, show_progress=False) \
+                .then(lambda: None, _js='()=>{refresh_style_localization();}')
 
 def dump_default_english_config():
     from modules.localization import dump_english_config