ci: bump actions/checkout from 4 to 5 (#4085)

Bumps [actions/checkout](https://github.com/actions/checkout) from 4 to 5.
- [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/v4...v5)

---
updated-dependencies:
- dependency-name: actions/checkout
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/CODEOWNERS

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

.github/workflows/build_container.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Log in to the Container registry
         uses: docker/login-action@v3

extras/BLIP/models/blip.py

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

extras/BLIP/models/blip_nlvr.py

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

extras/facexlib/detection/__init__.py

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

extras/facexlib/parsing/__init__.py

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

extras/ip_adapter.py

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

fooocus_version.py

@@ -1 +1 @@
-version = '2.5.2'
+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:",

launch.py

@@ -80,12 +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)
 

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

@@ -1223,6 +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
 

modules/config.py

@@ -520,10 +520,14 @@ for image_count in range(default_controlnet_image_count):
     image_count += 1
     default_ip_images[image_count] = get_config_item_or_set_default(
         key=f'default_ip_image_{image_count}',
-        default_value=None,
-        validator=lambda x: x is None or isinstance(x, str) and os.path.exists(x),
+        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,
@@ -698,10 +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

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

@@ -96,6 +96,7 @@ inpaint_options = [inpaint_option_default, inpaint_option_detail, inpaint_option
 
 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',

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/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
 
@@ -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
 
@@ -405,6 +397,7 @@ entry_with_update.py  [-h] [--listen [IP]] [--port PORT]
 ## Inline Prompt Features
 
 ### Wildcards
+
 Example prompt: `__color__ flower`
 
 Processed for positive and negative prompt.
@@ -416,6 +409,7 @@ You can also disable randomness and process a wildcard file from top to bottom b
 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.
@@ -434,23 +428,25 @@ Processed only for positive prompt.
 
 Applies a LoRA to the prompt. The LoRA file must be located in the `models/loras` directory.
 
-
 ## Advanced Features
 
 [Click here to browse the advanced features.](https://github.com/lllyasviel/Fooocus/discussions/117)
 
 ## Forks
-Fooocus also has many community forks, just like SD-WebUI's [vladmandic/automatic](https://github.com/vladmandic/automatic) and [anapnoe/stable-diffusion-webui-ux](https://github.com/anapnoe/stable-diffusion-webui-ux), for enthusiastic users who want to try!
+
+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> [mashb1t/Fooocus](https://github.com/mashb1t/Fooocus) </br> and so on ... |
-
-See also [About Forking and Promotion of Forks](https://github.com/lllyasviel/Fooocus/discussions/699).
+| [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
 
@@ -458,8 +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`:

update_log.md

@@ -1,3 +1,18 @@
+# [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

webui.py

@@ -337,10 +337,11 @@ with shared.gradio_root:
                             with gr.Column():
                                 describe_input_image = grh.Image(label='Image', source='upload', type='numpy', show_label=False)
                             with gr.Column():
-                                describe_method = gr.Radio(
+                                describe_methods = gr.CheckboxGroup(
                                     label='Content Type',
-                                    choices=[flags.describe_type_photo, flags.describe_type_anime],
-                                    value=flags.describe_type_photo)
+                                    choices=flags.describe_types,
+                                    value=modules.config.default_describe_content_type)
+                                describe_apply_styles = gr.Checkbox(label='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>')
@@ -1060,30 +1061,54 @@ with shared.gradio_root:
                 gr.Audio(interactive=False, value=notification_file, elem_id='audio_notification', visible=False)
                 break
 
-        def trigger_describe(mode, img):
-            if mode == flags.describe_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.describe_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"]
+        def trigger_describe(modes, img, apply_styles):
+            describe_prompts = []
+            styles = set()
 
-        describe_btn.click(trigger_describe, inputs=[describe_method, describe_input_image],
-                           outputs=[prompt, style_selections], show_progress=True, queue=True)
+            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=[describe_method, uov_input_image, prompt],
-                                   outputs=[prompt, style_selections], show_progress=True, queue=True)
+            uov_input_image.upload(trigger_auto_describe, inputs=[describe_methods, uov_input_image, prompt, describe_apply_styles],
+                                   outputs=[prompt, style_selections], show_progress=True, queue=True) \
+                .then(fn=style_sorter.sort_styles, inputs=style_selections, outputs=style_selections, queue=False, show_progress=False) \
+                .then(lambda: None, _js='()=>{refresh_style_localization();}')
 
             enhance_input_image.upload(lambda: gr.update(value=True), outputs=enhance_checkbox, queue=False, show_progress=False) \
-                .then(trigger_auto_describe, inputs=[describe_method, enhance_input_image, prompt], outputs=[prompt, style_selections], show_progress=True, queue=True)
+                .then(trigger_auto_describe, inputs=[describe_methods, enhance_input_image, prompt, describe_apply_styles],
+                      outputs=[prompt, style_selections], show_progress=True, queue=True) \
+                .then(fn=style_sorter.sort_styles, inputs=style_selections, outputs=style_selections, queue=False, show_progress=False) \
+                .then(lambda: None, _js='()=>{refresh_style_localization();}')
 
 def dump_default_english_config():
     from modules.localization import dump_english_config