Replies: 8 comments 5 replies
-
thanks for update |
Beta Was this translation helpful? Give feedback.
-
Some thing goes wrong for me:
I'm sorry for that. |
Beta Was this translation helpful? Give feedback.
-
you should remove annotator/downloading/normaldsine |
Beta Was this translation helpful? Give feedback.
-
When running the preprocessor there is such an error(I re-downloaded the dsin.pt file and still had this problem): Traceback (most recent call last):
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\gradio\routes.py", line 488, in run_predict
output = await app.get_blocks().process_api(
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\gradio\blocks.py", line 1431, in process_api
result = await self.call_function(
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\gradio\blocks.py", line 1103, in call_function
prediction = await anyio.to_thread.run_sync(
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\anyio\to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\anyio\_backends\_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\anyio\_backends\_asyncio.py", line 867, in run
result = context.run(func, *args)
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\gradio\utils.py", line 707, in wrapper
response = f(*args, **kwargs)
File "F:\sd-webui-aki-v4.6.1\extensions\sd-webui-controlnet\scripts\controlnet_ui\controlnet_ui_group.py", line 1015, in run_annotator
result, is_image = preprocessor(
File "F:\sd-webui-aki-v4.6.1\extensions\sd-webui-controlnet\scripts\utils.py", line 81, in decorated_func
return cached_func(*args, **kwargs)
File "F:\sd-webui-aki-v4.6.1\extensions\sd-webui-controlnet\scripts\utils.py", line 65, in cached_func
return func(*args, **kwargs)
File "F:\sd-webui-aki-v4.6.1\extensions\sd-webui-controlnet\scripts\global_state.py", line 37, in unified_preprocessor
return preprocessor_modules[preprocessor_name](*args, **kwargs)
File "F:\sd-webui-aki-v4.6.1\extensions\sd-webui-controlnet\scripts\processor.py", line 720, in normal_dsine
result = model_normal_dsine(img, new_fov=float(thr_a), iterations=int(thr_b), resulotion=res)
File "F:\sd-webui-aki-v4.6.1\extensions\sd-webui-controlnet\annotator\normaldsine\__init__.py", line 41, in __call__
self.load_model()
File "F:\sd-webui-aki-v4.6.1\extensions\sd-webui-controlnet\annotator\normaldsine\__init__.py", line 28, in load_model
model = DSINE()
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\dsine\models\dsine.py", line 56, in __init__
self.encoder = Encoder(B=5, pretrained=True)
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\dsine\models\submodules.py", line 24, in __init__
basemodel = geffnet.create_model('tf_efficientnet_b%s_ap' % B, pretrained=pretrained)
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\geffnet\model_factory.py", line 20, in create_model
model = create_fn(**model_kwargs)
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\geffnet\gen_efficientnet.py", line 1120, in tf_efficientnet_b5_ap
model = _gen_efficientnet(
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\geffnet\gen_efficientnet.py", line 544, in _gen_efficientnet
model = _create_model(model_kwargs, variant, pretrained)
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\geffnet\gen_efficientnet.py", line 290, in _create_model
load_pretrained(model, model_urls[variant])
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\geffnet\helpers.py", line 39, in load_pretrained
state_dict = load_state_dict_from_url(url, progress=False, map_location='cpu')
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\torch\hub.py", line 770, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location, weights_only=weights_only)
File "F:\sd-webui-aki-v4.6.1\modules\safe.py", line 108, in load
return load_with_extra(filename, *args, extra_handler=global_extra_handler, **kwargs)
File "F:\sd-webui-aki-v4.6.1\modules\safe.py", line 156, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\torch\serialization.py", line 1028, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "F:\sd-webui-aki-v4.6.1\python\lib\site-packages\torch\serialization.py", line 1264, in _legacy_load
typed_storage._untyped_storage._set_from_file(
RuntimeError: unexpected EOF, expected 259011 more bytes. The file might be corrupted. |
Beta Was this translation helpful? Give feedback.
-
I'm trying to load normal_dsine.pt but it wont show in controlnet. In A1111 it is listed under normal preprocessor but in webforge it just wont load, i have the normal_dsine.pt in these locations: "D:\AINOVO\WebForge\webui\models\ControlNet" and "D:\AINOVO\WebForge\webui\models\ControlNetPreprocessor". What am i doing wrong? |
Beta Was this translation helpful? Give feedback.
-
I've seen it before and it looks good, I'll test it out |
Beta Was this translation helpful? Give feedback.
-
I wish someone would cook this up to work with Forge's controlnet, because DSINE is honestly the best controlnet preprocessor, even depth anything pales in comparison. |
Beta Was this translation helpful? Give feedback.
-
Dsine
https://github.com/baegwangbin/DSINE
How to use
Use as normal bae
Model comparison
normal dsine has more details than others
input image
normal bae
normal dsine
normal midas
Beta Was this translation helpful? Give feedback.
All reactions