chore(deps): bump actions/checkout from 5 to 6

Bumps [actions/checkout](https://github.com/actions/checkout) from 5 to 6.
- [Release notes](https://github.com/actions/checkout/releases)
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/checkout/compare/v5...v6)

---
updated-dependencies:
- dependency-name: actions/checkout
  dependency-version: '6'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/CODEOWNERS

@@ -1 +1 @@
-*       @mashb1t
+*       @lllyasviel

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -1,77 +0,0 @@
-name: Bug Report
-description: Describe a problem
-title: "[Bug]: "
-labels: ["bug", "triage"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thank you for taking the time to fill out this bug report form!
-  - type: checkboxes
-    id: prerequisites
-    attributes:
-      label: Prerequisites
-      description: Please make sure to troubleshoot yourself before continuing.
-      options:
-        - label: I have read the [Troubleshooting Guide](https://github.com/lllyasviel/Fooocus/blob/main/troubleshoot.md)
-          required: true
-        - label: I have checked that this is not a duplicate of an already existing [issue](https://github.com/lllyasviel/Fooocus/issues)
-          required: true
-  - type: textarea
-    id: description
-    attributes:
-      label: Describe the problem
-      description: Also tell us, what did you expect to happen?
-      placeholder: "A clear and concise description of what the bug is."
-    validations:
-      required: true
-  - type: textarea
-    id: logs
-    attributes:
-      label: Full console log output
-      description: Please copy and paste the **full** console log here. You will make our job easier if you give a **full** log. This will be automatically formatted into code, so no need for backticks.
-      render: shell
-    validations:
-      required: true
-  - type: textarea
-    id: version
-    attributes:
-      label: Version
-      description: What version of Fooocus are you using? (see browser tab title or console log)
-      placeholder: "Example: Fooocus 2.1.855"
-    validations:
-      required: true
-  - type: dropdown
-    id: hosting
-    attributes:
-      label: Where are you running Fooocus?
-      multiple: false
-      options:
-        - Locally
-        - Locally with virtualisation (e.g. Docker)
-        - Cloud (Gradio)
-        - Cloud (other)
-    validations:
-      required: true
-  - type: input
-    id: operating-system
-    attributes:
-      label: Operating System
-      description: What operating system are you using?
-      placeholder: "Example: Windows 10"
-  - type: dropdown
-    id: browsers
-    attributes:
-      label: What browsers are you seeing the problem on?
-      multiple: true
-      options:
-        - Chrome
-        - Firefox
-        - Microsoft Edge
-        - Safari
-        - other
-    validations:
-      required: true
-  - type: markdown
-    attributes:
-      value: "Thank you for completing our form!"

.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
-        　3. 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
+        　1. Update Fooocus - sometimes things just need to be updated
+        　2. Backup and remove your config.txt - check if the issue is caused by bad configuration
+        　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)

.github/ISSUE_TEMPLATE/feature_request.yaml

@@ -1,34 +0,0 @@
-name: Feature request
-description: Suggest an idea for this project
-title: "[Feature]: "
-labels: ["enhancement"]
-body:
-  - type: markdown
-    attributes:
-      value: |
-        Thank you for taking the time to fill out this feature request form!
-  - type: checkboxes
-    id: prerequisites
-    attributes:
-      label: Prerequisites
-      options:
-        - label: I have checked that this is not a duplicate of an already existing [feature request](https://github.com/lllyasviel/Fooocus/issues)
-          required: true
-  - type: textarea
-    id: relation-to-problem
-    attributes:
-      label: Is your feature request related to a problem? Please describe.
-      placeholder: "A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-."
-    validations:
-      required: true
-  - type: textarea
-    id: description
-    attributes:
-      label: Describe the idea you'd like
-      placeholder: "A clear and concise description of what you want to happen."
-    validations:
-      required: true
-  - type: markdown
-    attributes:
-      value: "Thank you for completing our form!"

.github/workflows/build_container.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Log in to the Container registry
         uses: docker/login-action@v3

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_colab.ipynb

@@ -8,7 +8,7 @@
    },
    "outputs": [],
    "source": [
-    "!pip install pygit2==1.12.2\n",
+    "!pip install pygit2==1.15.1\n",
     "%cd /content\n",
     "!git clone https://github.com/lllyasviel/Fooocus.git\n",
     "%cd /content/Fooocus\n",

fooocus_version.py

@@ -1 +1 @@
-version = '2.5.0-rc1'
+version = '2.5.5'

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",

launch.py

@@ -21,7 +21,6 @@ import fooocus_version
 from build_launcher import build_launcher
 from modules.launch_util import is_installed, run, python, run_pip, requirements_met, delete_folder_content
 from modules.model_loader import load_file_from_url
-from modules import config
 
 REINSTALL_ALL = False
 TRY_INSTALL_XFORMERS = False
@@ -81,11 +80,13 @@ if args.gpu_device_id is not None:
     os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpu_device_id)
     print("Set device to:", args.gpu_device_id)
 
-if args.hf_mirror is not None : 
+if args.hf_mirror is not None:
     os.environ['HF_MIRROR'] = str(args.hf_mirror)
     print("Set hf_mirror to:", args.hf_mirror)
 
 from modules import config
+from modules.hash_cache import init_cache
+
 os.environ["U2NET_HOME"] = config.path_inpaint
 
 os.environ['GRADIO_TEMP_DIR'] = config.temp_path
@@ -100,6 +101,8 @@ if config.temp_path_cleanup_on_launch:
 
 
 def download_models(default_model, previous_default_models, checkpoint_downloads, embeddings_downloads, lora_downloads, vae_downloads):
+    from modules.util import get_file_from_folder_list
+
     for file_name, url in vae_approx_filenames:
         load_file_from_url(url=url, model_dir=config.path_vae_approx, file_name=file_name)
 
@@ -114,9 +117,9 @@ def download_models(default_model, previous_default_models, checkpoint_downloads
         return default_model, checkpoint_downloads
 
     if not args.always_download_new_model:
-        if not os.path.exists(os.path.join(config.paths_checkpoints[0], default_model)):
+        if not os.path.isfile(get_file_from_folder_list(default_model, config.paths_checkpoints)):
             for alternative_model_name in previous_default_models:
-                if os.path.exists(os.path.join(config.paths_checkpoints[0], alternative_model_name)):
+                if os.path.isfile(get_file_from_folder_list(alternative_model_name, config.paths_checkpoints)):
                     print(f'You do not have [{default_model}] but you have [{alternative_model_name}].')
                     print(f'Fooocus will use [{alternative_model_name}] to avoid downloading new models, '
                           f'but you are not using the latest models.')
@@ -126,11 +129,13 @@ def download_models(default_model, previous_default_models, checkpoint_downloads
                     break
 
     for file_name, url in checkpoint_downloads.items():
-        load_file_from_url(url=url, model_dir=config.paths_checkpoints[0], file_name=file_name)
+        model_dir = os.path.dirname(get_file_from_folder_list(file_name, config.paths_checkpoints))
+        load_file_from_url(url=url, model_dir=model_dir, file_name=file_name)
     for file_name, url in embeddings_downloads.items():
         load_file_from_url(url=url, model_dir=config.path_embeddings, file_name=file_name)
     for file_name, url in lora_downloads.items():
-        load_file_from_url(url=url, model_dir=config.paths_loras[0], file_name=file_name)
+        model_dir = os.path.dirname(get_file_from_folder_list(file_name, config.paths_loras))
+        load_file_from_url(url=url, model_dir=model_dir, file_name=file_name)
     for file_name, url in vae_downloads.items():
         load_file_from_url(url=url, model_dir=config.path_vae, file_name=file_name)
 
@@ -141,4 +146,7 @@ config.default_base_model_name, config.checkpoint_downloads = download_models(
     config.default_base_model_name, config.previous_default_models, config.checkpoint_downloads,
     config.embeddings_downloads, config.lora_downloads, config.vae_downloads)
 
+config.update_files()
+init_cache(config.model_filenames, config.paths_checkpoints, config.lora_filenames, config.paths_loras)
+
 from webui import *

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
-                )["params_ema"]
+                    decoder_load_path, map_location=lambda storage, loc: storage, 
+                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
-                )["params_ema"]
+                    decoder_load_path, map_location=lambda storage, loc: storage, 
+                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
-                )["params_ema"]
+                    decoder_load_path, map_location=lambda storage, loc: storage, 
+                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
 
 
@@ -197,7 +200,6 @@ def worker():
     from modules.upscaler import perform_upscale
     from modules.flags import Performance
     from modules.meta_parser import get_metadata_parser
-    from modules.translator import translate2en
 
     pid = os.getpid()
     print(f'Started worker with PID {pid}')
@@ -278,7 +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:
@@ -315,9 +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,
-                    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)
+        progressbar(async_task, current_progress, 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)
         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)
 
@@ -333,7 +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']),
@@ -388,7 +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
 
@@ -688,13 +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)
 
@@ -959,7 +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
@@ -980,7 +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
@@ -1014,7 +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
@@ -1022,7 +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
 
@@ -1040,7 +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':
@@ -1157,6 +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,
@@ -1212,6 +1223,8 @@ def worker():
             height, width, _ = async_task.enhance_input_image.shape
             # input image already provided, processing is skipped
             steps = 0
+            yield_result(async_task, async_task.enhance_input_image, current_progress, async_task.black_out_nsfw, False,
+                         async_task.disable_intermediate_results)
 
         all_steps = steps * async_task.image_number
 
@@ -1262,8 +1275,8 @@ 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 should_enhance
+        show_intermediate_results = len(tasks) > 1 or async_task.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} ...')
@@ -1276,7 +1289,8 @@ 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
@@ -1294,7 +1308,7 @@ 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
@@ -1303,9 +1317,14 @@ 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
@@ -1313,19 +1332,23 @@ 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':
@@ -1337,6 +1360,8 @@ 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':
@@ -1367,13 +1392,13 @@ 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 (
-                        dino_detection_count == 0 or not async_task.debugging_dino and sam_detection_on_mask_count == 0):
+                if enhance_mask_model == 'sam' and (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
 
@@ -1386,7 +1411,8 @@ 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):
@@ -1413,14 +1439,18 @@ 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

@@ -7,7 +7,6 @@ import args_manager
 import tempfile
 import modules.flags
 import modules.sdxl_styles
-from modules.hash_cache import init_cache
 
 from modules.model_loader import load_file_from_url
 from modules.extra_utils import makedirs_with_log, get_files_from_folder, try_eval_env_var
@@ -404,12 +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,
@@ -470,6 +493,69 @@ 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 == 'None' or isinstance(x, str) and os.path.exists(x),
+        expected_type=str
+    )
+
+    if default_ip_images[image_count] == 'None':
+        default_ip_images[image_count] = None
+
+    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,
@@ -527,12 +613,6 @@ 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,
@@ -563,6 +643,12 @@ 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,
@@ -585,6 +671,13 @@ 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',
@@ -609,10 +702,23 @@ default_inpaint_mask_cloth_category = get_config_item_or_set_default(
 default_inpaint_mask_sam_model = get_config_item_or_set_default(
     key='default_inpaint_mask_sam_model',
     default_value='vit_b',
-    validator=lambda x: x in [y[1] for y in modules.flags.inpaint_mask_sam_model if y[1] == x],
+    validator=lambda x: x in modules.flags.inpaint_mask_sam_model,
     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
@@ -889,7 +995,3 @@ def downloading_sam_vit_h():
         file_name='sam_vit_h_4b8939.pth'
     )
     return os.path.join(path_sam, 'sam_vit_h_4b8939.pth')
-
-
-update_files()
-init_cache(model_filenames, paths_checkpoints, lora_filenames, paths_loras)

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'
-desc_type_anime = 'Art/Anime'
+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',
@@ -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/hash_cache.py

@@ -4,8 +4,7 @@ from concurrent.futures import ThreadPoolExecutor
 from multiprocessing import cpu_count
 
 import args_manager
-from modules.util import get_file_from_folder_list
-from modules.util import sha256, HASH_SHA256_LENGTH
+from modules.util import sha256, HASH_SHA256_LENGTH, get_file_from_folder_list
 
 hash_cache_filename = 'hash_cache.txt'
 hash_cache = {}

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

@@ -9,7 +9,6 @@ from PIL import Image
 import fooocus_version
 import modules.config
 import modules.sdxl_styles
-from modules import hash_cache
 from modules.flags import MetadataScheme, Performance, Steps
 from modules.flags import SAMPLERS, CIVITAI_NO_KARRAS
 from modules.hash_cache import sha256_from_cache
@@ -605,9 +604,8 @@ def get_metadata_parser(metadata_scheme: MetadataScheme) -> MetadataParser:
             raise NotImplementedError
 
 
-def read_info_from_image(filepath) -> tuple[str | None, MetadataScheme | None]:
-    with Image.open(filepath) as image:
-        items = (image.info or {}).copy()
+def read_info_from_image(file) -> tuple[str | None, MetadataScheme | None]:
+    items = (file.info or {}).copy()
 
     parameters = items.pop('parameters', None)
     metadata_scheme = items.pop('fooocus_scheme', None)
@@ -616,7 +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:
-    path_outputs = modules.config.temp_path if args_manager.args.disable_image_log else modules.config.path_outputs
+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 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/style_sorter.py

@@ -37,7 +37,6 @@ def sort_styles(selected):
     global all_styles
     unselected = [y for y in all_styles if y not in selected]
     sorted_styles = selected + unselected
-    """
     try:
         with open('sorted_styles.json', 'wt', encoding='utf-8') as fp:
             json.dump(sorted_styles, fp, indent=4)
@@ -45,7 +44,6 @@ def sort_styles(selected):
         print('Write style sorting failed.')
         print(e)
     all_styles = sorted_styles
-    """
     return gr.CheckboxGroup.update(choices=sorted_styles)
 
 

modules/translator.py

@@ -1,15 +0,0 @@
-import translators
-from functools import lru_cache
-
-@lru_cache(maxsize=32, typed=False)
-def translate2en(text, element):
-    if not text:
-        return text
-
-    try:
-        result = translators.translate_text(text,to_language='en')
-        print(f'[Parameters] Translated {element}: {result}')
-        return result
-    except Exception as e:
-        print(f'[Parameters] Error during translation of {element}: {e}')
-        return text

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

@@ -1,40 +1,30 @@
 <div align=center>
 <img src="https://github.com/lllyasviel/Fooocus/assets/19834515/483fb86d-c9a2-4c20-997c-46dafc124f25">
-
-**Non-cherry-picked** random batch by just typing two words "forest elf", 
-
-without any parameter tweaking, without any strange prompt tags. 
-
-See also **non-cherry-picked** generalization and diversity tests [here](https://github.com/lllyasviel/Fooocus/discussions/2067) and [here](https://github.com/lllyasviel/Fooocus/discussions/808) and [here](https://github.com/lllyasviel/Fooocus/discussions/679) and [here](https://github.com/lllyasviel/Fooocus/discussions/679#realistic).
-
-In the entire open source community, only Fooocus can achieve this level of **non-cherry-picked** quality.
-
 </div>
 
-
 # Fooocus
 
-Fooocus is an image generating software (based on [Gradio](https://www.gradio.app/)).
+[>>> Click Here to Install Fooocus <<<](#download)
 
-Fooocus is a rethinking of Stable Diffusion and Midjourney’s designs:
+Fooocus is an image generating software (based on [Gradio](https://www.gradio.app/) <a href='https://github.com/gradio-app/gradio'><img src='https://img.shields.io/github/stars/gradio-app/gradio'></a>).
 
-* Learned from Stable Diffusion, the software is offline, open source, and free.
-
-* Learned from Midjourney, the manual tweaking is not needed, and users only need to focus on the prompts and images.
-
-Fooocus has included and automated [lots of inner optimizations and quality improvements](#tech_list). Users can forget all those difficult technical parameters, and just enjoy the interaction between human and computer to "explore new mediums of thought and expanding the imaginative powers of the human species" `[1]`.
-
-Fooocus has simplified the installation. Between pressing "download" and generating the first image, the number of needed mouse clicks is strictly limited to less than 3. Minimal GPU memory requirement is 4GB (Nvidia).
-
-`[1]` David Holz, 2019.
+Fooocus presents a rethinking of image generator designs. The software is offline, open source, and free, while at the same time, similar to many online image generators like Midjourney, the manual tweaking is not needed, and users only need to focus on the prompts and images. Fooocus has also simplified the installation: between pressing "download" and generating the first image, the number of needed mouse clicks is strictly limited to less than 3. Minimal GPU memory requirement is 4GB (Nvidia).
 
 **Recently many fake websites exist on Google when you search “fooocus”. Do not trust those – here is the only official source of Fooocus.**
 
-## [Installing Fooocus](#download)
+# Project Status: Limited Long-Term Support (LTS) with Bug Fixes Only
 
-# Moving from Midjourney to Fooocus
+The Fooocus project, built entirely on the **Stable Diffusion XL** architecture, is now in a state of limited long-term support (LTS) with bug fixes only. As the existing functionalities are considered as nearly free of programmartic issues (Thanks to [mashb1t](https://github.com/mashb1t)'s huge efforts), future updates will focus exclusively on addressing any bugs that may arise. 
 
-Using Fooocus is as easy as (probably easier than) Midjourney – but this does not mean we lack functionality. Below are the details.
+**There are no current plans to migrate to or incorporate newer model architectures.** However, this may change during time with the development of open-source community. For example, if the community converge to one single dominant method for image generation (which may really happen in half or one years given the current status), Fooocus may also migrate to that exact method.
+
+For those interested in utilizing newer models such as **Flux**, we recommend exploring alternative platforms such as [WebUI Forge](https://github.com/lllyasviel/stable-diffusion-webui-forge) (also from us), [ComfyUI/SwarmUI](https://github.com/comfyanonymous/ComfyUI). Additionally, several [excellent forks of Fooocus](https://github.com/lllyasviel/Fooocus?tab=readme-ov-file#forks) are available for experimentation.
+
+Again, recently many fake websites exist on Google when you search “fooocus”. Do **NOT** get Fooocus from those websites – this page is the only official source of Fooocus. We never have any website like such as “fooocus.com”, “fooocus.net”, “fooocus.co”, “fooocus.ai”, “fooocus.org”, “fooocus.pro”, “fooocus.one”. Those websites are ALL FAKE. **They have ABSOLUTLY no relationship to us. Fooocus is a 100% non-commercial offline open-source software.**
+
+# Features
+
+Below is a quick list using Midjourney's examples:
 
 | Midjourney | Fooocus |
 | - | - |
@@ -55,7 +45,7 @@ Using Fooocus is as easy as (probably easier than) Midjourney – but this does
 | InsightFace | Input Image -> Image Prompt -> Advanced -> FaceSwap |
 | Describe | Input Image -> Describe |
 
-We also have a few things borrowed from the best parts of LeonardoAI:
+Below is a quick list using LeonardoAI's examples:
 
 | LeonardoAI | Fooocus |
 | - | - |
@@ -63,7 +53,7 @@ We also have a few things borrowed from the best parts of LeonardoAI:
 | Advanced Sampler Parameters (like Contrast/Sharpness/etc) | Advanced -> Advanced -> Sampling Sharpness / etc |
 | User-friendly ControlNets | Input Image -> Image Prompt -> Advanced |
 
-Fooocus also developed many "fooocus-only" features for advanced users to get perfect results. [Click here to browse the advanced features.](https://github.com/lllyasviel/Fooocus/discussions/117)
+Also, [click here to browse the advanced features.](https://github.com/lllyasviel/Fooocus/discussions/117)
 
 # Download
 
@@ -71,7 +61,7 @@ Fooocus also developed many "fooocus-only" features for advanced users to get pe
 
 You can directly download Fooocus with:
 
-**[>>> Click here to download <<<](https://github.com/lllyasviel/Fooocus/releases/download/release/Fooocus_win64_2-1-831.7z)**
+**[>>> Click here to download <<<](https://github.com/lllyasviel/Fooocus/releases/download/v2.5.0/Fooocus_win64_2-5-0.7z)**
 
 After you download the file, please uncompress it and then run the "run.bat".
 
@@ -119,7 +109,7 @@ See also the common problems and troubleshoots [here](troubleshoot.md).
 
 ### Colab
 
-(Last tested - 2024 Mar 18 by [mashb1t](https://github.com/mashb1t))
+(Last tested - 2024 Aug 12 by [mashb1t](https://github.com/mashb1t))
 
 | Colab | Info
 | --- | --- |
@@ -225,7 +215,7 @@ Then run the `run.bat`.
 
 AMD is not intensively tested, however. The AMD support is in beta.
 
-For AMD, use `.\python_embeded\python.exe entry_with_update.py --directml --preset anime` or `.\python_embeded\python.exe entry_with_update.py --directml --preset realistic` for Fooocus Anime/Realistic Edition.
+For AMD, use `.\python_embeded\python.exe Fooocus\entry_with_update.py --directml --preset anime` or `.\python_embeded\python.exe Fooocus\entry_with_update.py --directml --preset realistic` for Fooocus Anime/Realistic Edition.
 
 ### Mac
 
@@ -303,7 +293,8 @@ In both ways the access is unauthenticated by default. You can add basic authent
 ## List of "Hidden" Tricks
 <a name="tech_list"></a>
 
-The below things are already inside the software, and **users do not need to do anything about these**.
+<details>
+<summary>Click to see a list of tricks. Those are based on SDXL and are not very up-to-date with latest models.</summary>
 
 1. GPT2-based [prompt expansion as a dynamic style "Fooocus V2".](https://github.com/lllyasviel/Fooocus/discussions/117#raw) (similar to Midjourney's hidden pre-processing and "raw" mode, or the LeonardoAI's Prompt Magic).
 2. Native refiner swap inside one single k-sampler. The advantage is that the refiner model can now reuse the base model's momentum (or ODE's history parameters) collected from k-sampling to achieve more coherent sampling. In Automatic1111's high-res fix and ComfyUI's node system, the base model and refiner use two independent k-samplers, which means the momentum is largely wasted, and the sampling continuity is broken. Fooocus uses its own advanced k-diffusion sampling that ensures seamless, native, and continuous swap in a refiner setup. (Update Aug 13: Actually, I discussed this with Automatic1111 several days ago, and it seems that the “native refiner swap inside one single k-sampler” is [merged]( https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12371) into the dev branch of webui. Great!)
@@ -319,6 +310,7 @@ The below things are already inside the software, and **users do not need to do
 12. Using automatic1111's method to normalize prompt emphasizing. This significantly improves results when users directly copy prompts from civitai.
 13. The joint swap system of the refiner now also supports img2img and upscale in a seamless way.
 14. CFG Scale and TSNR correction (tuned for SDXL) when CFG is bigger than 10.
+</details>
 
 ## Customization
 
@@ -371,15 +363,14 @@ 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]
-                      [--cache-path CACHE_PATH] [--in-browser]
-                      [--disable-in-browser]
+                      [--temp-path TEMP_PATH] [--cache-path CACHE_PATH]
+                      [--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]]
@@ -387,36 +378,75 @@ 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-low-vram | --always-no-vram | --always-cpu [CPU_NUM_THREADS]]
+                      [--always-gpu | --always-high-vram | --always-normal-vram | --always-low-vram | --always-no-vram | --always-cpu [CPU_NUM_THREADS]]
                       [--always-offload-from-vram]
-                      [--pytorch-deterministic] [--disable-server-log]  
-                      [--debug-mode] [--is-windows-embedded-python]     
-                      [--disable-server-info] [--multi-user] [--share]  
-                      [--preset PRESET] [--disable-preset-selection]    
+                      [--pytorch-deterministic] [--disable-server-log]
+                      [--debug-mode] [--is-windows-embedded-python]
+                      [--disable-server-info] [--multi-user] [--share]
+                      [--preset PRESET] [--disable-preset-selection]
                       [--language LANGUAGE]
-                      [--disable-offload-from-vram] [--theme THEME]     
-                      [--disable-image-log] [--disable-analytics]       
-                      [--disable-metadata] [--disable-preset-download]  
-                      [--enable-describe-uov-image]
+                      [--disable-offload-from-vram] [--theme THEME]
+                      [--disable-image-log] [--disable-analytics]
+                      [--disable-metadata] [--disable-preset-download]
+                      [--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)
 
-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!
+## Forks
+
+Below are some Forks to Fooocus:
 
 | 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 ... |
-
-See also [About Forking and Promotion of Forks](https://github.com/lllyasviel/Fooocus/discussions/699).
+| [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> [mashb1t/Fooocus](https://github.com/mashb1t/Fooocus) </br> and so on ... |
 
 ## Thanks
 
-Special thanks to [twri](https://github.com/twri) and [3Diva](https://github.com/3Diva) and [Marc K3nt3L](https://github.com/K3nt3L) for creating additional SDXL styles available in Fooocus. Thanks [daswer123](https://github.com/daswer123) for contributing the Canvas Zoom!
+Many thanks to [twri](https://github.com/twri) and [3Diva](https://github.com/3Diva) and [Marc K3nt3L](https://github.com/K3nt3L) for creating additional SDXL styles available in Fooocus. 
+
+The project starts from a mixture of [Stable Diffusion WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) and [ComfyUI](https://github.com/comfyanonymous/ComfyUI) codebases.
+
+Also, thanks [daswer123](https://github.com/daswer123) for contributing the Canvas Zoom!
 
 ## Update Log
 
@@ -424,8 +454,6 @@ The log is [here](update_log.md).
 
 ## Localization/Translation/I18N
 
-**We need your help!** Please help translate Fooocus into international languages.
-
 You can put json files in the `language` folder to translate the user interface.
 
 For example, below is the content of `Fooocus/language/example.json`:

requirements_versions.txt

@@ -1,22 +1,24 @@
-torchsde==0.2.5
-einops==0.4.1
-transformers==4.30.2
-safetensors==0.3.1
-accelerate==0.21.0
-pyyaml==6.0
-Pillow==9.2.0
-scipy==1.9.3
-tqdm==4.65.0
-psutil==5.9.5
-pytorch_lightning==1.9.4
-omegaconf==2.2.3
+torchsde==0.2.6
+einops==0.8.0
+transformers==4.42.4
+safetensors==0.4.3
+accelerate==0.32.1
+pyyaml==6.0.1
+pillow==10.4.0
+scipy==1.14.0
+tqdm==4.66.4
+psutil==6.0.0
+pytorch_lightning==2.3.3
+omegaconf==2.3.0
 gradio==3.41.2
-pygit2==1.12.2
-opencv-contrib-python==4.8.0.74
-httpx==0.24.1
-onnxruntime==1.16.3
-timm==0.9.2
-translators==5.9.2
+pygit2==1.15.1
+opencv-contrib-python-headless==4.10.0.84
+httpx==0.27.0
+onnxruntime==1.18.1
+timm==1.0.7
+numpy==1.26.4
+tokenizers==0.19.1
+packaging==24.1
 rembg==2.0.57
 groundingdino-py==0.4.0
 segment_anything==1.0

update_log.md

@@ -1,10 +1,48 @@
-# [2.5.0-rc1](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.0-rc1)
+# [2.5.5](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.5)
 
+* Fix colab inpaint issue by moving an import statement
+
+# [2.5.4](https://github.com/lllyasviel/Fooocus/releases/tag/v2.5.4)
+
+* Fix validation for default_ip_image_* and default_inpaint_mask_sam_model
+* Fix enhance mask debugging in combination with image sorting
+* Fix loading of checkpoints and LoRAs when using multiple directories in config and then switching presets
+
+# [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:
+1. Open a terminal in the Fooocus folder (location of config.txt) and run `git pull`
+2. Update packages
+   - Windows (installation through zip file): open a terminal in the Fooocus folder (location of config.txt) `..\python_embeded\python.exe -m pip install -r .\requirements_versions.txt` (Windows using embedded python, installation method zip file) or download Fooocus again (zip file attached to this release)
+   - other: manually update the packages using `python.exe -m pip install -r requirements_versions.txt` or use the docker image
+
+---
+
+* Update python dependencies, add segment_anything
 * Add enhance feature, which offers easy image refinement steps (similar to adetailer, but based on dynamic image detection instead of specific mask detection models). See [documentation](https://github.com/lllyasviel/Fooocus/discussions/3281).
 * Rewrite async worker code, make code much more reusable to allow iterations and improve reusability
 * Improve GroundingDINO and SAM image masking
 * Fix inference tensor version counter tracking issue for GroundingDINO after using Enhance (see [discussion](https://github.com/lllyasviel/Fooocus/discussions/3213))
-* Update python dependencies, add segment_anything
 * Move checkboxes Enable Mask Upload and Invert Mask When Generating from Developer Debug Mode to Inpaint Or Outpaint
 * Add persistent model cache for metadata. Use `--rebuild-hash-cache X` (X = int, number of CPU cores, default all) to manually rebuild the cache for all non-cached hashes
 * Rename `--enable-describe-uov-image` to `--enable-auto-describe-image`, now also works for enhance image upload

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.Tabs():
-                    with gr.TabItem(label='Upscale or Variation') as uov_tab:
+            with gr.Row(visible=modules.config.default_image_prompt_checkbox) as image_input_panel:
+                with gr.Tabs(selected=modules.config.default_selected_image_input_tab_id):
+                    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=default_end)
+                                            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_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],
-                                    value=flags.desc_type_photo)
-                                desc_btn = gr.Button(value='Describe this Image into Prompt')
-                                desc_image_size = gr.Textbox(label='Image Size and Recommended Size', elem_id='desc_image_size', visible=False)
+                                    choices=flags.describe_types,
+                                    value=modules.config.default_describe_content_type)
+                                describe_apply_styles = gr.Checkbox(label='Apply 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>')
 
                                 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,
-                                                        outputs=desc_image_size, show_progress=False, queue=False)
+                                describe_input_image.upload(trigger_show_image_properties, inputs=describe_input_image,
+                                                            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):
-                            parameters, metadata_scheme = modules.meta_parser.read_info_from_image(filepath)
+                        def trigger_metadata_preview(file):
+                            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.')
@@ -860,24 +886,6 @@ with shared.gradio_root:
                 refresh_files.click(refresh_files_clicked, [], refresh_files_output + lora_ctrls,
                                     queue=False, show_progress=False)
 
-            with gr.Tab(label='Audio'):
-                play_notification = gr.Checkbox(label='Play notification after rendering', value=False)
-                notification_file = 'notification.mp3'
-                if os.path.exists(notification_file):
-                    notification = gr.State(value=notification_file)
-                    notification_input = gr.Audio(label='Notification', interactive=True, elem_id='audio_notification', visible=False, show_edit_button=False)
-
-                    def play_notification_checked(r, notification):
-                        return gr.update(visible=r, value=notification if r else None)
-
-                    def notification_input_changed(notification_input, notification):
-                        if notification_input:
-                            notification = notification_input
-                        return notification
-
-                    play_notification.change(fn=play_notification_checked, inputs=[play_notification, notification], outputs=[notification_input], queue=False)
-                    notification_input.change(fn=notification_input_changed, inputs=[notification_input, notification], outputs=[notification], queue=False)
-
         state_is_generating = gr.State(False)
 
         load_data_outputs = [advanced_checkbox, image_number, prompt, negative_prompt, style_selections,
@@ -987,6 +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]
 
@@ -1013,8 +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):
-            parameters, metadata_scheme = modules.meta_parser.read_info_from_image(filepath)
+        def trigger_metadata_import(file, state_is_generating):
+            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 = {}
@@ -1045,30 +1056,59 @@ with shared.gradio_root:
                                     progress_html, progress_window, progress_gallery, gallery],
                            queue=False)
 
-        def trigger_describe(mode, img):
-            if mode == flags.desc_type_photo:
-                from extras.interrogate import default_interrogator as default_interrogator_photo
-                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"]
+        for notification_file in ['notification.ogg', 'notification.mp3']:
+            if os.path.exists(notification_file):
+                gr.Audio(interactive=False, value=notification_file, elem_id='audio_notification', visible=False)
+                break
 
-        desc_btn.click(trigger_describe, inputs=[desc_method, desc_input_image],
-                       outputs=[prompt, style_selections], show_progress=True, queue=True)
+        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
+                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],
-                                   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=[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