Merge pull request #3507 from lllyasviel/develop

Release 2.5.5

.github/CODEOWNERS

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

.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)

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 = '2.5.1'
+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

@@ -9,7 +9,7 @@ patch_all()
 
 class AsyncTask:
     def __init__(self, args):
-        from modules.flags import Performance, MetadataScheme, ip_list, controlnet_image_count, disabled
+        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
@@ -101,7 +101,7 @@ class AsyncTask:
             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()
@@ -689,13 +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)
 
@@ -1216,6 +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

@@ -403,12 +403,36 @@ default_performance = get_config_item_or_set_default(
     validator=lambda x: x in Performance.values(),
     expected_type=str
 )
+default_image_prompt_checkbox = get_config_item_or_set_default(
+    key='default_image_prompt_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
+default_enhance_checkbox = get_config_item_or_set_default(
+    key='default_enhance_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
 default_advanced_checkbox = get_config_item_or_set_default(
     key='default_advanced_checkbox',
     default_value=False,
     validator=lambda x: isinstance(x, bool),
     expected_type=bool
 )
+default_developer_debug_mode_checkbox = get_config_item_or_set_default(
+    key='default_developer_debug_mode_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
+default_image_prompt_advanced_checkbox = get_config_item_or_set_default(
+    key='default_image_prompt_advanced_checkbox',
+    default_value=False,
+    validator=lambda x: isinstance(x, bool),
+    expected_type=bool
+)
 default_max_image_number = get_config_item_or_set_default(
     key='default_max_image_number',
     default_value=32,
@@ -469,6 +493,69 @@ 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,
@@ -526,12 +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,
@@ -590,6 +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',
@@ -614,10 +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

@@ -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/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/sdxl_styles.py

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

modules/upscaler.py

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

readme.md

@@ -119,7 +119,7 @@ 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
 | --- | --- |

update_log.md

@@ -1,3 +1,23 @@
+# [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

webui.py

@@ -200,19 +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 = []
@@ -220,30 +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):
@@ -256,11 +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')
@@ -271,9 +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)
@@ -333,33 +332,34 @@ 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='pil')
                             metadata_json = gr.JSON(label='Metadata')
@@ -382,7 +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,
@@ -407,7 +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)
 
@@ -549,7 +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,
@@ -693,9 +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). ')
@@ -1061,30 +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.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"]
+        def trigger_describe(modes, img, apply_styles):
+            describe_prompts = []
+            styles = set()
 
-        desc_btn.click(trigger_describe, inputs=[desc_method, desc_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=[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