Merge pull request #3436 from lllyasviel/develop

fix: change wrong label for in describe apply styles checkbox

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -16,9 +16,9 @@ body:
       description: |
         Please perform basic debugging to see if your configuration is the cause of the issue.
         Basic debug procedure
-        　2. Update Fooocus - sometimes things just need to be updated
+        　1. Update Fooocus - sometimes things just need to be updated
-        　3. Backup and remove your config.txt - check if the issue is caused by bad configuration
+        　2. Backup and remove your config.txt - check if the issue is caused by bad configuration
-        　5. Try a fresh installation of Fooocus in a different directory - see if a clean installation solves the issue
+        　3. Try a fresh installation of Fooocus in a different directory - see if a clean installation solves the issue
         Before making a issue report please, check that the issue hasn't been reported recently.
       options:
         - label: The issue has not been resolved by following the [troubleshooting guide](https://github.com/lllyasviel/Fooocus/blob/main/troubleshoot.md)

args_manager.py

@@ -17,7 +17,7 @@ args_parser.parser.add_argument("--disable-offload-from-vram", action="store_tru
 
 args_parser.parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
 args_parser.parser.add_argument("--disable-image-log", action='store_true',
-                                help="Prevent writing images and logs to hard drive.")
+                                help="Prevent writing images and logs to the outputs folder.")
 
 args_parser.parser.add_argument("--disable-analytics", action='store_true',
                                 help="Disables analytics for Gradio.")
@@ -28,6 +28,9 @@ args_parser.parser.add_argument("--disable-metadata", action='store_true',
 args_parser.parser.add_argument("--disable-preset-download", action='store_true',
                                 help="Disables downloading models for presets", default=False)
 
+args_parser.parser.add_argument("--disable-enhance-output-sorting", action='store_true',
+                                help="Disables enhance output sorting for final image gallery.")
+
 args_parser.parser.add_argument("--enable-auto-describe-image", action='store_true',
                                 help="Enables automatic description of uov and enhance image when prompt is empty", default=False)
 

extras/BLIP/models/blip.py

@@ -216,9 +216,9 @@ def is_url(url_or_filename):
 def load_checkpoint(model,url_or_filename):
     if is_url(url_or_filename):
         cached_file = download_cached_file(url_or_filename, check_hash=False, progress=True)
-        checkpoint = torch.load(cached_file, map_location='cpu') 
+        checkpoint = torch.load(cached_file, map_location='cpu', weights_only=True) 
     elif os.path.isfile(url_or_filename):        
-        checkpoint = torch.load(url_or_filename, map_location='cpu') 
+        checkpoint = torch.load(url_or_filename, map_location='cpu', weights_only=True) 
     else:
         raise RuntimeError('checkpoint url or path is invalid')
         

extras/BLIP/models/blip_nlvr.py

@@ -78,9 +78,9 @@ def blip_nlvr(pretrained='',**kwargs):
 def load_checkpoint(model,url_or_filename):
     if is_url(url_or_filename):
         cached_file = download_cached_file(url_or_filename, check_hash=False, progress=True)
-        checkpoint = torch.load(cached_file, map_location='cpu') 
+        checkpoint = torch.load(cached_file, map_location='cpu', weights_only=True) 
     elif os.path.isfile(url_or_filename):        
-        checkpoint = torch.load(url_or_filename, map_location='cpu') 
+        checkpoint = torch.load(url_or_filename, map_location='cpu', weights_only=True) 
     else:
         raise RuntimeError('checkpoint url or path is invalid')
     state_dict = checkpoint['model']

extras/facexlib/detection/__init__.py

@@ -19,7 +19,7 @@ def init_detection_model(model_name, half=False, device='cuda', model_rootpath=N
         url=model_url, model_dir='facexlib/weights', progress=True, file_name=None, save_dir=model_rootpath)
 
     # TODO: clean pretrained model
-    load_net = torch.load(model_path, map_location=lambda storage, loc: storage)
+    load_net = torch.load(model_path, map_location=lambda storage, loc: storage, weights_only=True)
     # remove unnecessary 'module.'
     for k, v in deepcopy(load_net).items():
         if k.startswith('module.'):

extras/facexlib/parsing/__init__.py

@@ -17,7 +17,7 @@ def init_parsing_model(model_name='bisenet', half=False, device='cuda', model_ro
 
     model_path = load_file_from_url(
         url=model_url, model_dir='facexlib/weights', progress=True, file_name=None, save_dir=model_rootpath)
-    load_net = torch.load(model_path, map_location=lambda storage, loc: storage)
+    load_net = torch.load(model_path, map_location=lambda storage, loc: storage, weights_only=True)
     model.load_state_dict(load_net, strict=True)
     model.eval()
     model = model.to(device)

extras/ip_adapter.py

@@ -104,7 +104,7 @@ def load_ip_adapter(clip_vision_path, ip_negative_path, ip_adapter_path):
     offload_device = torch.device('cpu')
 
     use_fp16 = model_management.should_use_fp16(device=load_device)
-    ip_state_dict = torch.load(ip_adapter_path, map_location="cpu")
+    ip_state_dict = torch.load(ip_adapter_path, map_location="cpu", weights_only=True)
     plus = "latents" in ip_state_dict["image_proj"]
     cross_attention_dim = ip_state_dict["ip_adapter"]["1.to_k_ip.weight"].shape[1]
     sdxl = cross_attention_dim == 2048

fooocus_version.py

@@ -1 +1 @@
-version = '2.5.0'
+version = '2.5.3'

language/en.json

@@ -17,6 +17,7 @@
     "Content Type": "Content Type",
     "Photograph": "Photograph",
     "Art/Anime": "Art/Anime",
+    "Apply Styles": "Apply 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:",
@@ -68,6 +69,9 @@
     "Read wildcards in order": "Read wildcards in order",
     "Black Out NSFW": "Black Out NSFW",
     "Use black image if NSFW is detected.": "Use black image if NSFW is detected.",
+    "Save only final enhanced image": "Save only final enhanced image",
+    "Save Metadata to Images": "Save Metadata to Images",
+    "Adds parameters to generated images allowing manual regeneration.": "Adds parameters to generated images allowing manual regeneration.",
     "\ud83d\udcda History Log": "\uD83D\uDCDA History Log",
     "Image Style": "Image Style",
     "Fooocus V2": "Fooocus V2",

ldm_patched/ldm/modules/encoders/noise_aug_modules.py

@@ -8,7 +8,7 @@ class CLIPEmbeddingNoiseAugmentation(ImageConcatWithNoiseAugmentation):
         if clip_stats_path is None:
             clip_mean, clip_std = torch.zeros(timestep_dim), torch.ones(timestep_dim)
         else:
-            clip_mean, clip_std = torch.load(clip_stats_path, map_location="cpu")
+            clip_mean, clip_std = torch.load(clip_stats_path, map_location="cpu", weights_only=True)
         self.register_buffer("data_mean", clip_mean[None, :], persistent=False)
         self.register_buffer("data_std", clip_std[None, :], persistent=False)
         self.time_embed = Timestep(timestep_dim)

ldm_patched/modules/sd1_clip.py

@@ -326,7 +326,7 @@ def load_embed(embedding_name, embedding_directory, embedding_size, embed_key=No
                 except:
                     embed_out = safe_load_embed_zip(embed_path)
             else:
-                embed = torch.load(embed_path, map_location="cpu")
+                embed = torch.load(embed_path, map_location="cpu", weights_only=True)
     except Exception as e:
         print(traceback.format_exc())
         print()

ldm_patched/pfn/architecture/face/codeformer.py

@@ -377,15 +377,15 @@ class VQAutoEncoder(nn.Module):
         )
 
         if model_path is not None:
-            chkpt = torch.load(model_path, map_location="cpu")
+            chkpt = torch.load(model_path, map_location="cpu", weights_only=True)
             if "params_ema" in chkpt:
                 self.load_state_dict(
-                    torch.load(model_path, map_location="cpu")["params_ema"]
+                    torch.load(model_path, map_location="cpu", weights_only=True)["params_ema"]
                 )
                 logger.info(f"vqgan is loaded from: {model_path} [params_ema]")
             elif "params" in chkpt:
                 self.load_state_dict(
-                    torch.load(model_path, map_location="cpu")["params"]
+                    torch.load(model_path, map_location="cpu", weights_only=True)["params"]
                 )
                 logger.info(f"vqgan is loaded from: {model_path} [params]")
             else:

ldm_patched/pfn/architecture/face/gfpgan_bilinear_arch.py

@@ -273,8 +273,8 @@ class GFPGANBilinear(nn.Module):
         if decoder_load_path:
             self.stylegan_decoder.load_state_dict(
                 torch.load(
-                    decoder_load_path, map_location=lambda storage, loc: storage
+                    decoder_load_path, map_location=lambda storage, loc: storage, 
-                )["params_ema"]
+                weights_only=True)["params_ema"]
             )
         # fix decoder without updating params
         if fix_decoder:

ldm_patched/pfn/architecture/face/gfpganv1_arch.py

@@ -373,8 +373,8 @@ class GFPGANv1(nn.Module):
         if decoder_load_path:
             self.stylegan_decoder.load_state_dict(
                 torch.load(
-                    decoder_load_path, map_location=lambda storage, loc: storage
+                    decoder_load_path, map_location=lambda storage, loc: storage, 
-                )["params_ema"]
+                weights_only=True)["params_ema"]
             )
         # fix decoder without updating params
         if fix_decoder:

ldm_patched/pfn/architecture/face/gfpganv1_clean_arch.py

@@ -284,8 +284,8 @@ class GFPGANv1Clean(nn.Module):
         if decoder_load_path:
             self.stylegan_decoder.load_state_dict(
                 torch.load(
-                    decoder_load_path, map_location=lambda storage, loc: storage
+                    decoder_load_path, map_location=lambda storage, loc: storage, 
-                )["params_ema"]
+                weights_only=True)["params_ema"]
             )
         # fix decoder without updating params
         if fix_decoder:

modules/async_worker.py

@@ -9,7 +9,7 @@ patch_all()
 
 class AsyncTask:
     def __init__(self, args):
-        from modules.flags import Performance, MetadataScheme, ip_list, controlnet_image_count
+        from modules.flags import Performance, MetadataScheme, ip_list, disabled
         from modules.util import get_enabled_loras
         from modules.config import default_max_lora_number
         import args_manager
@@ -95,12 +95,13 @@ class AsyncTask:
         self.inpaint_advanced_masking_checkbox = args.pop()
         self.invert_mask_checkbox = args.pop()
         self.inpaint_erode_or_dilate = args.pop()
+        self.save_final_enhanced_image_only = args.pop() if not args_manager.args.disable_image_log else False
         self.save_metadata_to_images = args.pop() if not args_manager.args.disable_metadata else False
         self.metadata_scheme = MetadataScheme(
             args.pop()) if not args_manager.args.disable_metadata else MetadataScheme.FOOOCUS
 
         self.cn_tasks = {x: [] for x in ip_list}
-        for _ in range(controlnet_image_count):
+        for _ in range(modules.config.default_controlnet_image_count):
             cn_img = args.pop()
             cn_stop = args.pop()
             cn_weight = args.pop()
@@ -153,12 +154,14 @@ class AsyncTask:
                     enhance_inpaint_erode_or_dilate,
                     enhance_mask_invert
                 ])
-
+        self.should_enhance = self.enhance_checkbox and (self.enhance_uov_method != disabled.casefold() or len(self.enhance_ctrls) > 0)
+        self.images_to_enhance_count = 0
+        self.enhance_stats = {}
 
 async_tasks = []
 
 
-class EarlyReturnException:
+class EarlyReturnException(BaseException):
     pass
 
 
@@ -277,7 +280,7 @@ def worker():
     def process_task(all_steps, async_task, callback, controlnet_canny_path, controlnet_cpds_path, current_task_id,
                      denoising_strength, final_scheduler_name, goals, initial_latent, steps, switch, positive_cond,
                      negative_cond, task, loras, tiled, use_expansion, width, height, base_progress, preparation_steps,
-                     total_count, show_intermediate_results):
+                     total_count, show_intermediate_results, persist_image=True):
         if async_task.last_stop is not False:
             ldm_patched.modules.model_management.interrupt_current_processing()
         if 'cn' in goals:
@@ -314,9 +317,8 @@ def worker():
         if modules.config.default_black_out_nsfw or async_task.black_out_nsfw:
             progressbar(async_task, current_progress, 'Checking for NSFW content ...')
             imgs = default_censor(imgs)
-        progressbar(async_task, current_progress,
+        progressbar(async_task, current_progress, f'Saving image {current_task_id + 1}/{total_count} to system ...')
-                    f'Saving image {current_task_id + 1}/{total_count} to system ...')
+        img_paths = save_and_log(async_task, height, imgs, task, use_expansion, width, loras, persist_image)
-        img_paths = save_and_log(async_task, height, imgs, task, use_expansion, width, loras)
         yield_result(async_task, img_paths, current_progress, async_task.black_out_nsfw, False,
                      do_not_show_finished_images=not show_intermediate_results or async_task.disable_intermediate_results)
 
@@ -332,7 +334,7 @@ def worker():
             async_task.adaptive_cfg
         )
 
-    def save_and_log(async_task, height, imgs, task, use_expansion, width, loras) -> list:
+    def save_and_log(async_task, height, imgs, task, use_expansion, width, loras, persist_image=True) -> list:
         img_paths = []
         for x in imgs:
             d = [('Prompt', 'prompt', task['log_positive_prompt']),
@@ -387,7 +389,7 @@ def worker():
             d.append(('Metadata Scheme', 'metadata_scheme',
                       async_task.metadata_scheme.value if async_task.save_metadata_to_images else async_task.save_metadata_to_images))
             d.append(('Version', 'version', 'Fooocus v' + fooocus_version.version))
-            img_paths.append(log(x, d, metadata_parser, async_task.output_format, task))
+            img_paths.append(log(x, d, metadata_parser, async_task.output_format, task, persist_image))
 
         return img_paths
 
@@ -687,13 +689,20 @@ def worker():
 
             task_styles = async_task.style_selections.copy()
             if use_style:
+                placeholder_replaced = False
+
                 for j, s in enumerate(task_styles):
                     if s == random_style_name:
                         s = get_random_style(task_rng)
                         task_styles[j] = s
-                    p, n = apply_style(s, positive=task_prompt)
+                    p, n, style_has_placeholder = apply_style(s, positive=task_prompt)
+                    if style_has_placeholder:
+                        placeholder_replaced = True
                     positive_basic_workloads = positive_basic_workloads + p
                     negative_basic_workloads = negative_basic_workloads + n
+
+                if not placeholder_replaced:
+                    positive_basic_workloads = [task_prompt] + positive_basic_workloads
             else:
                 positive_basic_workloads.append(task_prompt)
 
@@ -958,7 +967,7 @@ def worker():
                         inpaint_engine, inpaint_respective_field, inpaint_strength,
                         prompt, negative_prompt, final_scheduler_name, goals, height, img, mask,
                         preparation_steps, steps, switch, tiled, total_count, use_expansion, use_style,
-                        use_synthetic_refiner, width, show_intermediate_results=True):
+                        use_synthetic_refiner, width, show_intermediate_results=True, persist_image=True):
         base_model_additional_loras = []
         inpaint_head_model_path = None
         inpaint_parameterized = inpaint_engine != 'None'  # inpaint_engine = None, improve detail
@@ -979,7 +988,7 @@ def worker():
                     progressbar(async_task, current_progress, 'Checking for NSFW content ...')
                     img = default_censor(img)
                 progressbar(async_task, current_progress, f'Saving image {current_task_id + 1}/{total_count} to system ...')
-                uov_image_path = log(img, d, output_format=async_task.output_format)
+                uov_image_path = log(img, d, output_format=async_task.output_format, persist_image=persist_image)
                 yield_result(async_task, uov_image_path, current_progress, async_task.black_out_nsfw, False,
                              do_not_show_finished_images=not show_intermediate_results or async_task.disable_intermediate_results)
                 return current_progress, img, prompt, negative_prompt
@@ -1013,7 +1022,8 @@ def worker():
                                                          final_scheduler_name, goals, initial_latent, steps, switch,
                                                          task_enhance['c'], task_enhance['uc'], task_enhance, loras,
                                                          tiled, use_expansion, width, height, current_progress,
-                                                         preparation_steps, total_count, show_intermediate_results)
+                                                         preparation_steps, total_count, show_intermediate_results,
+                                                         persist_image)
 
         del task_enhance['c'], task_enhance['uc']  # Save memory
         return current_progress, imgs[0], prompt, negative_prompt
@@ -1021,7 +1031,7 @@ def worker():
     def enhance_upscale(all_steps, async_task, base_progress, callback, controlnet_canny_path, controlnet_cpds_path,
                         current_task_id, denoising_strength, done_steps_inpainting, done_steps_upscaling, enhance_steps,
                         prompt, negative_prompt, final_scheduler_name, height, img, preparation_steps, switch, tiled,
-                        total_count, use_expansion, use_style, use_synthetic_refiner, width):
+                        total_count, use_expansion, use_style, use_synthetic_refiner, width, persist_image=True):
         # reset inpaint worker to prevent tensor size issues and not mix upscale and inpainting
         inpaint_worker.current_task = None
 
@@ -1039,7 +1049,7 @@ def worker():
                     controlnet_cpds_path, current_progress, current_task_id, denoising_strength, False,
                     'None', 0.0, 0.0, prompt, negative_prompt, final_scheduler_name,
                     goals_enhance, height, img, None, preparation_steps, steps, switch, tiled, total_count,
-                    use_expansion, use_style, use_synthetic_refiner, width)
+                    use_expansion, use_style, use_synthetic_refiner, width, persist_image=persist_image)
 
             except ldm_patched.modules.model_management.InterruptProcessingException:
                 if async_task.last_stop == 'skip':
@@ -1156,6 +1166,8 @@ def worker():
             current_progress += 1
             progressbar(async_task, current_progress, 'Image processing ...')
 
+        should_enhance = async_task.enhance_checkbox and (async_task.enhance_uov_method != flags.disabled.casefold() or len(async_task.enhance_ctrls) > 0)
+
         if 'vary' in goals:
             async_task.uov_input_image, denoising_strength, initial_latent, width, height, current_progress = apply_vary(
                 async_task, async_task.uov_method, denoising_strength, async_task.uov_input_image, switch,
@@ -1261,8 +1273,8 @@ def worker():
                 int(current_progress + async_task.callback_steps),
                 f'Sampling step {step + 1}/{total_steps}, image {current_task_id + 1}/{total_count} ...', y)])
 
-        should_enhance = async_task.enhance_checkbox and (async_task.enhance_uov_method != flags.disabled.casefold() or len(async_task.enhance_ctrls) > 0)
+        show_intermediate_results = len(tasks) > 1 or async_task.should_enhance
-        show_intermediate_results = len(tasks) > 1 or should_enhance
+        persist_image = not async_task.should_enhance or not async_task.save_final_enhanced_image_only
 
         for current_task_id, task in enumerate(tasks):
             progressbar(async_task, current_progress, f'Preparing task {current_task_id + 1}/{async_task.image_number} ...')
@@ -1275,7 +1287,8 @@ def worker():
                                                                  initial_latent, async_task.steps, switch, task['c'],
                                                                  task['uc'], task, loras, tiled, use_expansion, width,
                                                                  height, current_progress, preparation_steps,
-                                                                 async_task.image_number, show_intermediate_results)
+                                                                 async_task.image_number, show_intermediate_results,
+                                                                 persist_image)
 
                 current_progress = int(preparation_steps + (100 - preparation_steps) / float(all_steps) * async_task.steps * (current_task_id + 1))
                 images_to_enhance += imgs
@@ -1293,7 +1306,7 @@ def worker():
             execution_time = time.perf_counter() - execution_start_time
             print(f'Generating and saving time: {execution_time:.2f} seconds')
 
-        if not should_enhance:
+        if not async_task.should_enhance:
             print(f'[Enhance] Skipping, preconditions aren\'t met')
             stop_processing(async_task, processing_start_time)
             return
@@ -1302,9 +1315,14 @@ def worker():
 
         active_enhance_tabs = len(async_task.enhance_ctrls)
         should_process_enhance_uov = async_task.enhance_uov_method != flags.disabled.casefold()
+        enhance_uov_before = False
+        enhance_uov_after = False
         if should_process_enhance_uov:
             active_enhance_tabs += 1
+            enhance_uov_before = async_task.enhance_uov_processing_order == flags.enhancement_uov_before
+            enhance_uov_after = async_task.enhance_uov_processing_order == flags.enhancement_uov_after
         total_count = len(images_to_enhance) * active_enhance_tabs
+        async_task.images_to_enhance_count = len(images_to_enhance)
 
         base_progress = current_progress
         current_task_id = -1
@@ -1312,19 +1330,23 @@ def worker():
         done_steps_inpainting = 0
         enhance_steps, _, _, _ = apply_overrides(async_task, async_task.original_steps, height, width)
         exception_result = None
-        for img in images_to_enhance:
+        for index, img in enumerate(images_to_enhance):
+            async_task.enhance_stats[index] = 0
             enhancement_image_start_time = time.perf_counter()
 
             last_enhance_prompt = async_task.prompt
             last_enhance_negative_prompt = async_task.negative_prompt
 
-            if should_process_enhance_uov and async_task.enhance_uov_processing_order == flags.enhancement_uov_before:
+            if enhance_uov_before:
                 current_task_id += 1
+                persist_image = not async_task.save_final_enhanced_image_only or active_enhance_tabs == 0
                 current_task_id, done_steps_inpainting, done_steps_upscaling, img, exception_result = enhance_upscale(
                     all_steps, async_task, base_progress, callback, controlnet_canny_path, controlnet_cpds_path,
                     current_task_id, denoising_strength, done_steps_inpainting, done_steps_upscaling, enhance_steps,
                     async_task.prompt, async_task.negative_prompt, final_scheduler_name, height, img, preparation_steps,
-                    switch, tiled, total_count, use_expansion, use_style, use_synthetic_refiner, width)
+                    switch, tiled, total_count, use_expansion, use_style, use_synthetic_refiner, width, persist_image)
+                async_task.enhance_stats[index] += 1
+
                 if exception_result == 'continue':
                     continue
                 elif exception_result == 'break':
@@ -1336,6 +1358,8 @@ def worker():
                 current_progress = int(base_progress + (100 - preparation_steps) / float(all_steps) * (done_steps_upscaling + done_steps_inpainting))
                 progressbar(async_task, current_progress, f'Preparing enhancement {current_task_id + 1}/{total_count} ...')
                 enhancement_task_start_time = time.perf_counter()
+                is_last_enhance_for_image = (current_task_id + 1) % active_enhance_tabs == 0 and not enhance_uov_after
+                persist_image = not async_task.save_final_enhanced_image_only or is_last_enhance_for_image
 
                 extras = {}
                 if enhance_mask_model == 'sam':
@@ -1366,13 +1390,13 @@ def worker():
                     async_task.yields.append(['preview', (current_progress, 'Loading ...', mask)])
                     yield_result(async_task, mask, current_progress, async_task.black_out_nsfw, False,
                                  async_task.disable_intermediate_results)
+                    async_task.enhance_stats[index] += 1
 
                 print(f'[Enhance] {dino_detection_count} boxes detected')
                 print(f'[Enhance] {sam_detection_count} segments detected in boxes')
                 print(f'[Enhance] {sam_detection_on_mask_count} segments applied to mask')
 
-                if enhance_mask_model == 'sam' and (
+                if enhance_mask_model == 'sam' and (dino_detection_count == 0 or not async_task.debugging_dino and sam_detection_on_mask_count == 0):
-                        dino_detection_count == 0 or not async_task.debugging_dino and sam_detection_on_mask_count == 0):
                     print(f'[Enhance] No "{enhance_mask_dino_prompt_text}" detected, skipping')
                     continue
 
@@ -1385,7 +1409,8 @@ def worker():
                         enhance_inpaint_engine, enhance_inpaint_respective_field, enhance_inpaint_strength,
                         enhance_prompt, enhance_negative_prompt, final_scheduler_name, goals_enhance, height, img, mask,
                         preparation_steps, enhance_steps, switch, tiled, total_count, use_expansion, use_style,
-                        use_synthetic_refiner, width)
+                        use_synthetic_refiner, width, persist_image=persist_image)
+                    async_task.enhance_stats[index] += 1
 
                     if (should_process_enhance_uov and async_task.enhance_uov_processing_order == flags.enhancement_uov_after
                             and async_task.enhance_uov_prompt_type == flags.enhancement_uov_prompt_type_last_filled):
@@ -1412,14 +1437,18 @@ def worker():
             if exception_result == 'break':
                 break
 
-            if should_process_enhance_uov and async_task.enhance_uov_processing_order == flags.enhancement_uov_after:
+            if enhance_uov_after:
                 current_task_id += 1
+                # last step in enhance, always save
+                persist_image = True
                 current_task_id, done_steps_inpainting, done_steps_upscaling, img, exception_result = enhance_upscale(
                     all_steps, async_task, base_progress, callback, controlnet_canny_path, controlnet_cpds_path,
                     current_task_id, denoising_strength, done_steps_inpainting, done_steps_upscaling, enhance_steps,
                     last_enhance_prompt, last_enhance_negative_prompt, final_scheduler_name, height, img,
                     preparation_steps, switch, tiled, total_count, use_expansion, use_style, use_synthetic_refiner,
-                    width)
+                    width, persist_image)
+                async_task.enhance_stats[index] += 1
+                
                 if exception_result == 'continue':
                     continue
                 elif exception_result == 'break':

modules/config.py

@@ -403,12 +403,36 @@ default_performance = get_config_item_or_set_default(
     validator=lambda x: x in Performance.values(),
     expected_type=str
 )
+default_image_prompt_checkbox = get_config_item_or_set_default(
+    key='default_image_prompt_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
+default_enhance_checkbox = get_config_item_or_set_default(
+    key='default_enhance_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
 default_advanced_checkbox = get_config_item_or_set_default(
     key='default_advanced_checkbox',
     default_value=False,
     validator=lambda x: isinstance(x, bool),
     expected_type=bool
 )
+default_developer_debug_mode_checkbox = get_config_item_or_set_default(
+    key='default_developer_debug_mode_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
+default_image_prompt_advanced_checkbox = get_config_item_or_set_default(
+    key='default_image_prompt_advanced_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
 default_max_image_number = get_config_item_or_set_default(
     key='default_max_image_number',
     default_value=32,
@@ -469,6 +493,65 @@ default_inpaint_engine_version = get_config_item_or_set_default(
     validator=lambda x: x in modules.flags.inpaint_engine_versions,
     expected_type=str
 )
+default_selected_image_input_tab_id = get_config_item_or_set_default(
+    key='default_selected_image_input_tab_id',
+    default_value=modules.flags.default_input_image_tab,
+    validator=lambda x: x in modules.flags.input_image_tab_ids,
+    expected_type=str
+)
+default_uov_method = get_config_item_or_set_default(
+    key='default_uov_method',
+    default_value=modules.flags.disabled,
+    validator=lambda x: x in modules.flags.uov_list,
+    expected_type=str
+)
+default_controlnet_image_count = get_config_item_or_set_default(
+    key='default_controlnet_image_count',
+    default_value=4,
+    validator=lambda x: isinstance(x, int) and x > 0,
+    expected_type=int
+)
+default_ip_images = {}
+default_ip_stop_ats = {}
+default_ip_weights = {}
+default_ip_types = {}
+
+for image_count in range(default_controlnet_image_count):
+    image_count += 1
+    default_ip_images[image_count] = get_config_item_or_set_default(
+        key=f'default_ip_image_{image_count}',
+        default_value=None,
+        validator=lambda x: x is None or isinstance(x, str) and os.path.exists(x),
+        expected_type=str
+    )
+    default_ip_types[image_count] = get_config_item_or_set_default(
+        key=f'default_ip_type_{image_count}',
+        default_value=modules.flags.default_ip,
+        validator=lambda x: x in modules.flags.ip_list,
+        expected_type=str
+    )
+
+    default_end, default_weight = modules.flags.default_parameters[default_ip_types[image_count]]
+
+    default_ip_stop_ats[image_count] = get_config_item_or_set_default(
+        key=f'default_ip_stop_at_{image_count}',
+        default_value=default_end,
+        validator=lambda x: isinstance(x, float) and 0 <= x <= 1,
+        expected_type=float
+    )
+    default_ip_weights[image_count] = get_config_item_or_set_default(
+        key=f'default_ip_weight_{image_count}',
+        default_value=default_weight,
+        validator=lambda x: isinstance(x, float) and 0 <= x <= 2,
+        expected_type=float
+    )
+
+default_inpaint_advanced_masking_checkbox = get_config_item_or_set_default(
+    key='default_inpaint_advanced_masking_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
 default_inpaint_method = get_config_item_or_set_default(
     key='default_inpaint_method',
     default_value=modules.flags.inpaint_option_default,
@@ -526,12 +609,6 @@ default_enhance_tabs = get_config_item_or_set_default(
     validator=lambda x: isinstance(x, int) and 1 <= x <= 5,
     expected_type=int
 )
-default_enhance_checkbox = get_config_item_or_set_default(
-    key='default_enhance_checkbox',
-    default_value=False,
-    validator=lambda x: isinstance(x, bool),
-    expected_type=bool
-)
 default_enhance_uov_method = get_config_item_or_set_default(
     key='default_enhance_uov_method',
     default_value=modules.flags.disabled,
@@ -562,6 +639,12 @@ default_black_out_nsfw = get_config_item_or_set_default(
     validator=lambda x: isinstance(x, bool),
     expected_type=bool
 )
+default_save_only_final_enhanced_image = get_config_item_or_set_default(
+    key='default_save_only_final_enhanced_image',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
 default_save_metadata_to_images = get_config_item_or_set_default(
     key='default_save_metadata_to_images',
     default_value=False,
@@ -584,6 +667,13 @@ metadata_created_by = get_config_item_or_set_default(
 example_inpaint_prompts = [[x] for x in example_inpaint_prompts]
 example_enhance_detection_prompts = [[x] for x in example_enhance_detection_prompts]
 
+default_invert_mask_checkbox = get_config_item_or_set_default(
+    key='default_invert_mask_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
+
 default_inpaint_mask_model = get_config_item_or_set_default(
     key='default_inpaint_mask_model',
     default_value='isnet-general-use',
@@ -612,6 +702,19 @@ default_inpaint_mask_sam_model = get_config_item_or_set_default(
     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/core.py

@@ -231,7 +231,7 @@ def get_previewer(model):
     if vae_approx_filename in VAE_approx_models:
         VAE_approx_model = VAE_approx_models[vae_approx_filename]
     else:
-        sd = torch.load(vae_approx_filename, map_location='cpu')
+        sd = torch.load(vae_approx_filename, map_location='cpu', weights_only=True)
         VAE_approx_model = VAEApprox()
         VAE_approx_model.load_state_dict(sd)
         del sd

modules/flags.py

@@ -67,6 +67,9 @@ default_vae = 'Default (model)'
 
 refiner_swap_method = 'joint'
 
+default_input_image_tab = 'uov_tab'
+input_image_tab_ids = ['uov_tab', 'ip_tab', 'inpaint_tab', 'describe_tab', 'enhance_tab', 'metadata_tab']
+
 cn_ip = "ImagePrompt"
 cn_ip_face = "FaceSwap"
 cn_canny = "PyraCanny"
@@ -91,8 +94,9 @@ inpaint_option_detail = 'Improve Detail (face, hand, eyes, etc.)'
 inpaint_option_modify = 'Modify Content (add objects, change background, etc.)'
 inpaint_options = [inpaint_option_default, inpaint_option_detail, inpaint_option_modify]
 
-desc_type_photo = 'Photograph'
+describe_type_photo = 'Photograph'
-desc_type_anime = 'Art/Anime'
+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',
@@ -113,8 +117,6 @@ metadata_scheme = [
     (f'{MetadataScheme.A1111.value} (plain text)', MetadataScheme.A1111.value),
 ]
 
-controlnet_image_count = 4
-
 
 class OutputFormat(Enum):
     PNG = 'png'

modules/inpaint_worker.py

@@ -196,7 +196,7 @@ class InpaintWorker:
 
         if inpaint_head_model is None:
             inpaint_head_model = InpaintHead()
-            sd = torch.load(inpaint_head_model_path, map_location='cpu')
+            sd = torch.load(inpaint_head_model_path, map_location='cpu', weights_only=True)
             inpaint_head_model.load_state_dict(sd)
 
         feed = torch.cat([

modules/meta_parser.py

@@ -604,9 +604,8 @@ def get_metadata_parser(metadata_scheme: MetadataScheme) -> MetadataParser:
             raise NotImplementedError
 
 
-def read_info_from_image(filepath) -> tuple[str | None, MetadataScheme | None]:
+def read_info_from_image(file) -> tuple[str | None, MetadataScheme | None]:
-    with Image.open(filepath) as image:
+    items = (file.info or {}).copy()
-        items = (image.info or {}).copy()
 
     parameters = items.pop('parameters', None)
     metadata_scheme = items.pop('fooocus_scheme', None)
@@ -615,7 +614,7 @@ def read_info_from_image(filepath) -> tuple[str | None, MetadataScheme | None]:
     if parameters is not None and is_json(parameters):
         parameters = json.loads(parameters)
     elif exif is not None:
-        exif = image.getexif()
+        exif = file.getexif()
         # 0x9286 = UserComment
         parameters = exif.get(0x9286, None)
         # 0x927C = MakerNote

modules/private_logger.py

@@ -21,8 +21,8 @@ def get_current_html_path(output_format=None):
     return html_name
 
 
-def log(img, metadata, metadata_parser: MetadataParser | None = None, output_format=None, task=None) -> str:
+def log(img, metadata, metadata_parser: MetadataParser | None = None, output_format=None, task=None, persist_image=True) -> str:
-    path_outputs = modules.config.temp_path if args_manager.args.disable_image_log else modules.config.path_outputs
+    path_outputs = modules.config.temp_path if args_manager.args.disable_image_log or not persist_image else modules.config.path_outputs
     output_format = output_format if output_format else modules.config.default_output_format
     date_string, local_temp_filename, only_name = generate_temp_filename(folder=path_outputs, extension=output_format)
     os.makedirs(os.path.dirname(local_temp_filename), exist_ok=True)

modules/sdxl_styles.py

@@ -59,7 +59,7 @@ def get_random_style(rng: Random) -> str:
 
 def apply_style(style, positive):
     p, n = styles[style]
-    return p.replace('{prompt}', positive).splitlines(), n.splitlines()
+    return p.replace('{prompt}', positive).splitlines(), n.splitlines(), '{prompt}' in p
 
 
 def get_words(arrays, total_mult, index):

modules/upscaler.py

@@ -17,7 +17,7 @@ def perform_upscale(img):
 
     if model is None:
         model_filename = downloading_upscale_model()
-        sd = torch.load(model_filename)
+        sd = torch.load(model_filename, weights_only=True)
         sdo = OrderedDict()
         for k, v in sd.items():
             sdo[k.replace('residual_block_', 'RDB')] = v

readme.md

@@ -371,15 +371,14 @@ entry_with_update.py  [-h] [--listen [IP]] [--port PORT]
                       [--hf-mirror HF_MIRROR]
                       [--external-working-path PATH [PATH ...]]
                       [--output-path OUTPUT_PATH]
-                      [--temp-path TEMP_PATH]
+                      [--temp-path TEMP_PATH] [--cache-path CACHE_PATH]
-                      [--cache-path CACHE_PATH] [--in-browser]
+                      [--in-browser] [--disable-in-browser]
-                      [--disable-in-browser]
                       [--gpu-device-id DEVICE_ID]
                       [--async-cuda-allocation | --disable-async-cuda-allocation]
                       [--disable-attention-upcast]
                       [--all-in-fp32 | --all-in-fp16]
                       [--unet-in-bf16 | --unet-in-fp16 | --unet-in-fp8-e4m3fn | --unet-in-fp8-e5m2]
-                      [--vae-in-fp16 | --vae-in-fp32 | --vae-in-bf16]   
+                      [--vae-in-fp16 | --vae-in-fp32 | --vae-in-bf16]
                       [--vae-in-cpu]
                       [--clip-in-fp8-e4m3fn | --clip-in-fp8-e5m2 | --clip-in-fp16 | --clip-in-fp32]
                       [--directml [DIRECTML_DEVICE]]
@@ -387,30 +386,65 @@ entry_with_update.py  [-h] [--listen [IP]] [--port PORT]
                       [--preview-option [none,auto,fast,taesd]]
                       [--attention-split | --attention-quad | --attention-pytorch]
                       [--disable-xformers]
-                      [--always-gpu | --always-high-vram | --always-normal-vram |
+                      [--always-gpu | --always-high-vram | --always-normal-vram | --always-low-vram | --always-no-vram | --always-cpu [CPU_NUM_THREADS]]
-                      --always-low-vram | --always-no-vram | --always-cpu [CPU_NUM_THREADS]]
                       [--always-offload-from-vram]
-                      [--pytorch-deterministic] [--disable-server-log]  
+                      [--pytorch-deterministic] [--disable-server-log]
-                      [--debug-mode] [--is-windows-embedded-python]     
+                      [--debug-mode] [--is-windows-embedded-python]
-                      [--disable-server-info] [--multi-user] [--share]  
+                      [--disable-server-info] [--multi-user] [--share]
-                      [--preset PRESET] [--disable-preset-selection]    
+                      [--preset PRESET] [--disable-preset-selection]
                       [--language LANGUAGE]
-                      [--disable-offload-from-vram] [--theme THEME]     
+                      [--disable-offload-from-vram] [--theme THEME]
-                      [--disable-image-log] [--disable-analytics]       
+                      [--disable-image-log] [--disable-analytics]
-                      [--disable-metadata] [--disable-preset-download]  
+                      [--disable-metadata] [--disable-preset-download]
-                      [--enable-describe-uov-image]
+                      [--disable-enhance-output-sorting]
+                      [--enable-auto-describe-image]
                       [--always-download-new-model]
+                      [--rebuild-hash-cache [CPU_NUM_THREADS]]
 ```
 
+## Inline Prompt Features
+
+### Wildcards
+Example prompt: `__color__ flower`
+
+Processed for positive and negative prompt.
+
+Selects a random wildcard from a predefined list of options, in this case the `wildcards/color.txt` file. 
+The wildcard will be replaced with a random color (randomness based on seed). 
+You can also disable randomness and process a wildcard file from top to bottom by enabling the checkbox `Read wildcards in order` in Developer Debug Mode.
+
+Wildcards can be nested and combined, and multiple wildcards can be used in the same prompt (example see `wildcards/color_flower.txt`).
+
+### Array Processing
+Example prompt: `[[red, green, blue]] flower`
+
+Processed only for positive prompt.
+
+Processes the array from left to right, generating a separate image for each element in the array. In this case 3 images would be generated, one for each color.
+Increase the image number to 3 to generate all 3 variants.
+
+Arrays can not be nested, but multiple arrays can be used in the same prompt.
+Does support inline LoRAs as array elements!
+
+### Inline LoRAs
+
+Example prompt: `flower <lora:sunflowers:1.2>`
+
+Processed only for positive prompt.
+
+Applies a LoRA to the prompt. The LoRA file must be located in the `models/loras` directory.
+
+
 ## Advanced Features
 
 [Click here to browse the advanced features.](https://github.com/lllyasviel/Fooocus/discussions/117)
 
+## Forks
 Fooocus also has many community forks, just like SD-WebUI's [vladmandic/automatic](https://github.com/vladmandic/automatic) and [anapnoe/stable-diffusion-webui-ux](https://github.com/anapnoe/stable-diffusion-webui-ux), for enthusiastic users who want to try!
 
 | Fooocus' forks |
 | - |
-| [fenneishi/Fooocus-Control](https://github.com/fenneishi/Fooocus-Control) </br>[runew0lf/RuinedFooocus](https://github.com/runew0lf/RuinedFooocus) </br> [MoonRide303/Fooocus-MRE](https://github.com/MoonRide303/Fooocus-MRE) </br> [metercai/SimpleSDXL](https://github.com/metercai/SimpleSDXL) </br> and so on ... |
+| [fenneishi/Fooocus-Control](https://github.com/fenneishi/Fooocus-Control) </br>[runew0lf/RuinedFooocus](https://github.com/runew0lf/RuinedFooocus) </br> [MoonRide303/Fooocus-MRE](https://github.com/MoonRide303/Fooocus-MRE) </br> [metercai/SimpleSDXL](https://github.com/metercai/SimpleSDXL) </br> [mashb1t/Fooocus](https://github.com/mashb1t/Fooocus) </br> and so on ... |
 
 See also [About Forking and Promotion of Forks](https://github.com/lllyasviel/Fooocus/discussions/699).
 

update_log.md

@@ -1,3 +1,23 @@
+# [2.5.3](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.3)
+
+* Only load weights from non-safetensors files, preventing harmful code injection
+* Add checkbox for applying/resetting styles when describing images, also allowing multiple describe content types
+
+# [2.5.2](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.2)
+
+* Fix not adding positive prompt when styles didn't have a {prompt} placeholder in the positive prompt
+* Extend config settings for input image, see list in [PR](https://github.com/lllyasviel/Fooocus/pull/3382)
+
+# [2.5.1](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.1)
+
+* Update download URL in readme
+* Increase speed of metadata loading
+* Fix reading of metadata from jpeg, jpg and webp (exif)
+* Fix debug preprocessor
+* Update attributes and add inline prompt features section to readme
+* Add checkbox, config and handling for saving only the final enhanced image. Use config `default_save_only_final_enhanced_image`, default False.
+* Add sorting of final images when enhanced is enabled. Use argument `--disable-enhance-output-sorting` to disable.
+
 # [2.5.0](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.0)
 
 This version includes various package updates. If the auto-update doesn't work you can do one of the following:

webui.py

@@ -73,6 +73,9 @@ def generate_clicked(task: worker.AsyncTask):
                     gr.update(visible=True, value=product), \
                     gr.update(visible=False)
             if flag == 'finish':
+                if not args_manager.args.disable_enhance_output_sorting:
+                    product = sort_enhance_images(product, task)
+
                 yield gr.update(visible=False), \
                     gr.update(visible=False), \
                     gr.update(visible=False), \
@@ -90,6 +93,25 @@ def generate_clicked(task: worker.AsyncTask):
     return
 
 
+def sort_enhance_images(images, task):
+    if not task.should_enhance or len(images) <= task.images_to_enhance_count:
+        return images
+
+    sorted_images = []
+    walk_index = task.images_to_enhance_count
+
+    for index, enhanced_img in enumerate(images[:task.images_to_enhance_count]):
+        sorted_images.append(enhanced_img)
+        if index not in task.enhance_stats:
+            continue
+        target_index = walk_index + task.enhance_stats[index]
+        if walk_index < len(images) and target_index <= len(images):
+            sorted_images += images[walk_index:target_index]
+        walk_index += task.enhance_stats[index]
+
+    return sorted_images
+
+
 def inpaint_mode_change(mode, inpaint_engine_version):
     assert mode in modules.flags.inpaint_options
 
@@ -178,19 +200,19 @@ with shared.gradio_root:
                     stop_button.click(stop_clicked, inputs=currentTask, outputs=currentTask, queue=False, show_progress=False, _js='cancelGenerateForever')
                     skip_button.click(skip_clicked, inputs=currentTask, outputs=currentTask, queue=False, show_progress=False)
             with gr.Row(elem_classes='advanced_check_row'):
-                input_image_checkbox = gr.Checkbox(label='Input Image', value=False, container=False, elem_classes='min_check')
+                input_image_checkbox = gr.Checkbox(label='Input Image', value=modules.config.default_image_prompt_checkbox, container=False, elem_classes='min_check')
                 enhance_checkbox = gr.Checkbox(label='Enhance', value=modules.config.default_enhance_checkbox, container=False, elem_classes='min_check')
                 advanced_checkbox = gr.Checkbox(label='Advanced', value=modules.config.default_advanced_checkbox, container=False, elem_classes='min_check')
-            with gr.Row(visible=False) as image_input_panel:
+            with gr.Row(visible=modules.config.default_image_prompt_checkbox) as image_input_panel:
-                with gr.Tabs():
+                with gr.Tabs(selected=modules.config.default_selected_image_input_tab_id):
-                    with gr.TabItem(label='Upscale or Variation') as uov_tab:
+                    with gr.Tab(label='Upscale or Variation', id='uov_tab') as uov_tab:
                         with gr.Row():
                             with gr.Column():
                                 uov_input_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False)
                             with gr.Column():
-                                uov_method = gr.Radio(label='Upscale or Variation:', choices=flags.uov_list, value=flags.disabled)
+                                uov_method = gr.Radio(label='Upscale or Variation:', choices=flags.uov_list, value=modules.config.default_uov_method)
                                 gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/390" target="_blank">\U0001F4D4 Documentation</a>')
-                    with gr.TabItem(label='Image Prompt') as ip_tab:
+                    with gr.Tab(label='Image Prompt', id='ip_tab') as ip_tab:
                         with gr.Row():
                             ip_images = []
                             ip_types = []
@@ -198,30 +220,29 @@ with shared.gradio_root:
                             ip_weights = []
                             ip_ctrls = []
                             ip_ad_cols = []
-                            for _ in range(flags.controlnet_image_count):
+                            for image_count in range(modules.config.default_controlnet_image_count):
+                                image_count += 1
                                 with gr.Column():
-                                    ip_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False, height=300)
+                                    ip_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False, height=300, value=modules.config.default_ip_images[image_count])
                                     ip_images.append(ip_image)
                                     ip_ctrls.append(ip_image)
-                                    with gr.Column(visible=False) as ad_col:
+                                    with gr.Column(visible=modules.config.default_image_prompt_advanced_checkbox) as ad_col:
                                         with gr.Row():
-                                            default_end, default_weight = flags.default_parameters[flags.default_ip]
+                                            ip_stop = gr.Slider(label='Stop At', minimum=0.0, maximum=1.0, step=0.001, value=modules.config.default_ip_stop_ats[image_count])
-
-                                            ip_stop = gr.Slider(label='Stop At', minimum=0.0, maximum=1.0, step=0.001, value=default_end)
                                             ip_stops.append(ip_stop)
                                             ip_ctrls.append(ip_stop)
 
-                                            ip_weight = gr.Slider(label='Weight', minimum=0.0, maximum=2.0, step=0.001, value=default_weight)
+                                            ip_weight = gr.Slider(label='Weight', minimum=0.0, maximum=2.0, step=0.001, value=modules.config.default_ip_weights[image_count])
                                             ip_weights.append(ip_weight)
                                             ip_ctrls.append(ip_weight)
 
-                                        ip_type = gr.Radio(label='Type', choices=flags.ip_list, value=flags.default_ip, container=False)
+                                        ip_type = gr.Radio(label='Type', choices=flags.ip_list, value=modules.config.default_ip_types[image_count], container=False)
                                         ip_types.append(ip_type)
                                         ip_ctrls.append(ip_type)
 
                                         ip_type.change(lambda x: flags.default_parameters[x], inputs=[ip_type], outputs=[ip_stop, ip_weight], queue=False, show_progress=False)
                                     ip_ad_cols.append(ad_col)
-                        ip_advanced = gr.Checkbox(label='Advanced', value=False, container=False)
+                        ip_advanced = gr.Checkbox(label='Advanced', value=modules.config.default_image_prompt_advanced_checkbox, container=False)
                         gr.HTML('* \"Image Prompt\" is powered by Fooocus Image Mixture Engine (v1.0.1). <a href="https://github.com/lllyasviel/Fooocus/discussions/557" target="_blank">\U0001F4D4 Documentation</a>')
 
                         def ip_advance_checked(x):
@@ -234,11 +255,11 @@ with shared.gradio_root:
                                            outputs=ip_ad_cols + ip_types + ip_stops + ip_weights,
                                            queue=False, show_progress=False)
 
-                    with gr.TabItem(label='Inpaint or Outpaint') as inpaint_tab:
+                    with gr.Tab(label='Inpaint or Outpaint', id='inpaint_tab') as inpaint_tab:
                         with gr.Row():
                             with gr.Column():
                                 inpaint_input_image = grh.Image(label='Image', source='upload', type='numpy', tool='sketch', height=500, brush_color="#FFFFFF", elem_id='inpaint_canvas', show_label=False)
-                                inpaint_advanced_masking_checkbox = gr.Checkbox(label='Enable Advanced Masking Features', value=False)
+                                inpaint_advanced_masking_checkbox = gr.Checkbox(label='Enable Advanced Masking Features', value=modules.config.default_inpaint_advanced_masking_checkbox)
                                 inpaint_mode = gr.Dropdown(choices=modules.flags.inpaint_options, value=modules.config.default_inpaint_method, label='Method')
                                 inpaint_additional_prompt = gr.Textbox(placeholder="Describe what you want to inpaint.", elem_id='inpaint_additional_prompt', label='Inpaint Additional Prompt', visible=False)
                                 outpaint_selections = gr.CheckboxGroup(choices=['Left', 'Right', 'Top', 'Bottom'], value=[], label='Outpaint Direction')
@@ -249,9 +270,9 @@ with shared.gradio_root:
                                 gr.HTML('* Powered by Fooocus Inpaint Engine <a href="https://github.com/lllyasviel/Fooocus/discussions/414" target="_blank">\U0001F4D4 Documentation</a>')
                                 example_inpaint_prompts.click(lambda x: x[0], inputs=example_inpaint_prompts, outputs=inpaint_additional_prompt, show_progress=False, queue=False)
 
-                            with gr.Column(visible=False) as inpaint_mask_generation_col:
+                            with gr.Column(visible=modules.config.default_inpaint_advanced_masking_checkbox) as inpaint_mask_generation_col:
                                 inpaint_mask_image = grh.Image(label='Mask Upload', source='upload', type='numpy', tool='sketch', height=500, brush_color="#FFFFFF", mask_opacity=1, elem_id='inpaint_mask_canvas')
-                                invert_mask_checkbox = gr.Checkbox(label='Invert Mask When Generating', value=False)
+                                invert_mask_checkbox = gr.Checkbox(label='Invert Mask When Generating', value=modules.config.default_invert_mask_checkbox)
                                 inpaint_mask_model = gr.Dropdown(label='Mask generation model',
                                                                  choices=flags.inpaint_mask_models,
                                                                  value=modules.config.default_inpaint_mask_model)
@@ -311,40 +332,41 @@ with shared.gradio_root:
                                                                    example_inpaint_mask_dino_prompt_text],
                                                           queue=False, show_progress=False)
 
-                    with gr.TabItem(label='Describe') as desc_tab:
+                    with gr.Tab(label='Describe', id='describe_tab') as describe_tab:
                         with gr.Row():
                             with gr.Column():
-                                desc_input_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False)
+                                describe_input_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False)
                             with gr.Column():
-                                desc_method = gr.Radio(
+                                describe_methods = gr.CheckboxGroup(
                                     label='Content Type',
-                                    choices=[flags.desc_type_photo, flags.desc_type_anime],
+                                    choices=flags.describe_types,
-                                    value=flags.desc_type_photo)
+                                    value=modules.config.default_describe_content_type)
-                                desc_btn = gr.Button(value='Describe this Image into Prompt')
+                                describe_apply_styles = gr.Checkbox(label='Apply Styles', value=modules.config.default_describe_apply_prompts_checkbox)
-                                desc_image_size = gr.Textbox(label='Image Size and Recommended Size', elem_id='desc_image_size', visible=False)
+                                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>')
 
                                 def trigger_show_image_properties(image):
                                     value = modules.util.get_image_size_info(image, modules.flags.sdxl_aspect_ratios)
                                     return gr.update(value=value, visible=True)
 
-                                desc_input_image.upload(trigger_show_image_properties, inputs=desc_input_image,
+                                describe_input_image.upload(trigger_show_image_properties, inputs=describe_input_image,
-                                                        outputs=desc_image_size, show_progress=False, queue=False)
+                                                            outputs=describe_image_size, show_progress=False, queue=False)
 
-                    with gr.TabItem(label='Enhance') as enhance_tab:
+                    with gr.Tab(label='Enhance', id='enhance_tab') as enhance_tab:
                         with gr.Row():
                             with gr.Column():
                                 enhance_input_image = grh.Image(label='Use with Enhance, skips image generation', source='upload', type='numpy')
                                 gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/3281" target="_blank">\U0001F4D4 Documentation</a>')
 
-                    with gr.TabItem(label='Metadata') as metadata_tab:
+                    with gr.Tab(label='Metadata', id='metadata_tab') as metadata_tab:
                         with gr.Column():
-                            metadata_input_image = grh.Image(label='For images created by Fooocus', source='upload', type='filepath')
+                            metadata_input_image = grh.Image(label='For images created by Fooocus', source='upload', type='pil')
                             metadata_json = gr.JSON(label='Metadata')
                             metadata_import_button = gr.Button(value='Apply Metadata')
 
-                        def trigger_metadata_preview(filepath):
+                        def trigger_metadata_preview(file):
-                            parameters, metadata_scheme = modules.meta_parser.read_info_from_image(filepath)
+                            parameters, metadata_scheme = modules.meta_parser.read_info_from_image(file)
 
                             results = {}
                             if parameters is not None:
@@ -360,7 +382,7 @@ with shared.gradio_root:
 
             with gr.Row(visible=modules.config.default_enhance_checkbox) as enhance_input_panel:
                 with gr.Tabs():
-                    with gr.TabItem(label='Upscale or Variation'):
+                    with gr.Tab(label='Upscale or Variation'):
                         with gr.Row():
                             with gr.Column():
                                 enhance_uov_method = gr.Radio(label='Upscale or Variation:', choices=flags.uov_list,
@@ -385,7 +407,7 @@ with shared.gradio_root:
                     enhance_inpaint_engine_ctrls = []
                     enhance_inpaint_update_ctrls = []
                     for index in range(modules.config.default_enhance_tabs):
-                        with gr.TabItem(label=f'#{index + 1}') as enhance_tab_item:
+                        with gr.Tab(label=f'#{index + 1}') as enhance_tab_item:
                             enhance_enabled = gr.Checkbox(label='Enable', value=False, elem_classes='min_check',
                                                           container=False)
 
@@ -527,7 +549,7 @@ with shared.gradio_root:
             uov_tab.select(lambda: 'uov', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
             inpaint_tab.select(lambda: 'inpaint', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
             ip_tab.select(lambda: 'ip', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
-            desc_tab.select(lambda: 'desc', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
+            describe_tab.select(lambda: 'desc', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
             enhance_tab.select(lambda: 'enhance', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
             metadata_tab.select(lambda: 'metadata', outputs=current_tab, queue=False, _js=down_js, show_progress=False)
             enhance_checkbox.change(lambda x: gr.update(visible=x), inputs=enhance_checkbox,
@@ -671,9 +693,9 @@ with shared.gradio_root:
                                       value=modules.config.default_sample_sharpness,
                                       info='Higher value means image and texture are sharper.')
                 gr.HTML('<a href="https://github.com/lllyasviel/Fooocus/discussions/117" target="_blank">\U0001F4D4 Documentation</a>')
-                dev_mode = gr.Checkbox(label='Developer Debug Mode', value=False, container=False)
+                dev_mode = gr.Checkbox(label='Developer Debug Mode', value=modules.config.default_developer_debug_mode_checkbox, container=False)
 
-                with gr.Column(visible=False) as dev_tools:
+                with gr.Column(visible=modules.config.default_developer_debug_mode_checkbox) as dev_tools:
                     with gr.Tab(label='Debug Tools'):
                         adm_scaler_positive = gr.Slider(label='Positive ADM Guidance Scaler', minimum=0.1, maximum=3.0,
                                                         step=0.001, value=1.5, info='The scaler multiplied to positive ADM (use 1.0 to disable). ')
@@ -748,6 +770,10 @@ with shared.gradio_root:
                                               inputs=black_out_nsfw, outputs=disable_preview, queue=False,
                                               show_progress=False)
 
+                        if not args_manager.args.disable_image_log:
+                            save_final_enhanced_image_only = gr.Checkbox(label='Save only final enhanced image',
+                                                                         value=modules.config.default_save_only_final_enhanced_image)
+
                         if not args_manager.args.disable_metadata:
                             save_metadata_to_images = gr.Checkbox(label='Save Metadata to Images', value=modules.config.default_save_metadata_to_images,
                                                                   info='Adds parameters to generated images allowing manual regeneration.')
@@ -969,6 +995,9 @@ with shared.gradio_root:
         ctrls += freeu_ctrls
         ctrls += inpaint_ctrls
 
+        if not args_manager.args.disable_image_log:
+            ctrls += [save_final_enhanced_image_only]
+
         if not args_manager.args.disable_metadata:
             ctrls += [save_metadata_to_images, metadata_scheme]
 
@@ -995,8 +1024,8 @@ with shared.gradio_root:
 
         load_parameter_button.click(modules.meta_parser.load_parameter_button_click, inputs=[prompt, state_is_generating, inpaint_mode], outputs=load_data_outputs, queue=False, show_progress=False)
 
-        def trigger_metadata_import(filepath, state_is_generating):
+        def trigger_metadata_import(file, state_is_generating):
-            parameters, metadata_scheme = modules.meta_parser.read_info_from_image(filepath)
+            parameters, metadata_scheme = modules.meta_parser.read_info_from_image(file)
             if parameters is None:
                 print('Could not find metadata in the image!')
                 parsed_parameters = {}
@@ -1032,30 +1061,54 @@ with shared.gradio_root:
                 gr.Audio(interactive=False, value=notification_file, elem_id='audio_notification', visible=False)
                 break
 
-        def trigger_describe(mode, img):
+        def trigger_describe(modes, img, apply_styles):
-            if mode == flags.desc_type_photo:
+            describe_prompts = []
-                from extras.interrogate import default_interrogator as default_interrogator_photo
+            styles = set()
-                return default_interrogator_photo(img), ["Fooocus V2", "Fooocus Enhance", "Fooocus Sharp"]
-            if mode == flags.desc_type_anime:
-                from extras.wd14tagger import default_interrogator as default_interrogator_anime
-                return default_interrogator_anime(img), ["Fooocus V2", "Fooocus Masterpiece"]
-            return mode, ["Fooocus V2"]
 
-        desc_btn.click(trigger_describe, inputs=[desc_method, desc_input_image],
+            if flags.describe_type_photo in modes:
-                       outputs=[prompt, style_selections], show_progress=True, queue=True)
+                from extras.interrogate import default_interrogator as default_interrogator_photo
+                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
+                describe_prompts.append(default_interrogator_anime(img))
+                styles.update(["Fooocus V2", "Fooocus Masterpiece"])
+
+            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=[desc_method, uov_input_image, prompt],
+            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)
+                                   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=[desc_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