automatic
automatic copied to clipboard
vladmandic
[Issue] Stable Video Diffusion not working
Issue Description
Stable Video Diffusion safetensors not load. Diffusers failed loading. Stable Video Diffusion pipeline not found.
The SVD pipeline is not available in the drop down menu for pipelines.
venv\Lib\site-packages\diffusers\pipelines\stable_video_diffusion exist.
Version Platform Description
21:22:28-500514 INFO Starting SD.Next 21:22:28-508761 INFO Logger: file="D:\Stable Diffusion\Vladmandic\sdnext.log" level=DEBUG size=65 mode=create 21:22:28-513027 INFO Python 3.10.6 on Windows 21:22:28-720886 INFO Version: app=sd.next updated=2024-05-07 hash=e081f232 branch=master url=https://github.com/vladmandic/automatic/tree/master 21:22:29-644654 INFO Platform: arch=AMD64 cpu=Intel64 Family 6 Model 60 Stepping 3, GenuineIntel system=Windows release=Windows-10-10.0.22631-SP0 python=3.10.6 21:22:29-646659 DEBUG Setting environment tuning 21:22:29-649673 DEBUG HF cache folder: %temp%.cache\huggingface\hub 21:22:29-651722 DEBUG Torch overrides: cuda=False rocm=False ipex=False diml=False openvino=False 21:22:29-653902 DEBUG Torch allowed: cuda=True rocm=True ipex=True diml=True openvino=True 21:22:29-655905 INFO nVidia CUDA toolkit detected: nvidia-smi present 21:22:29-658919 DEBUG Installing torch: torch torchvision --index-url https://download.pytorch.org/whl/cu121 21:22:29-883012 DEBUG Repository update time: Tue May 7 21:11:45 2024 21:22:29-885002 INFO Startup: standard 21:22:29-886001 INFO Verifying requirements 21:22:29-892253 INFO Verifying packages 21:22:29-894269 INFO Verifying submodules 21:22:53-331436 DEBUG Submodule: extensions-builtin/sd-extension-chainner / main 21:22:53-478252 DEBUG Submodule: extensions-builtin/sd-extension-system-info / main 21:22:53-593755 DEBUG Submodule: extensions-builtin/sd-webui-agent-scheduler / main 21:22:53-725421 DEBUG Submodule: extensions-builtin/sd-webui-controlnet / main 21:22:53-948768 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-images-browser / main 21:22:54-054924 DEBUG Submodule: extensions-builtin/stable-diffusion-webui-rembg / master 21:22:54-166577 DEBUG Submodule: modules/k-diffusion / master 21:22:54-295608 DEBUG Submodule: wiki / master 21:22:54-369392 DEBUG Register paths 21:22:54-520457 DEBUG Installed packages: 253 21:22:54-523457 DEBUG Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg'] 21:22:54-809195 DEBUG Running extension installer: D:\Stable Diffusion\Vladmandic\extensions-builtin\sd-extension-system-info\install.py 21:22:55-395347 DEBUG Running extension installer: D:\Stable Diffusion\Vladmandic\extensions-builtin\sd-webui-agent-scheduler\install.py 21:22:55-911993 DEBUG Running extension installer: D:\Stable Diffusion\Vladmandic\extensions-builtin\stable-diffusion-webui-images-browser\install.py 21:22:56-378711 DEBUG Running extension installer: D:\Stable Diffusion\Vladmandic\extensions-builtin\stable-diffusion-webui-rembg\install.py 21:22:56-855484 DEBUG Extensions all: [] 21:22:56-857485 INFO Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info', 'sd-webui-agent-scheduler', 'stable-diffusion-webui-images-browser', 'stable-diffusion-webui-rembg'] 21:22:56-859495 INFO Verifying requirements 21:22:56-864777 DEBUG Setup complete without errors: 1715455377
Relevant log output
21:23:42-178114 DEBUG Load model: existing=False target=D:\Stable Diffusion\Vladmandic\models\Stable-diffusion\Stable Video Diffusion\svd_xt.safetensors info=None
21:23:42-224968 DEBUG Desired Torch parameters: dtype=FP16 no-half=False no-half-vae=False upscast=False
21:23:42-224968 INFO Setting Torch parameters: device=cuda dtype=torch.float16 vae=torch.float16 unet=torch.float16 context=no_grad fp16=True bf16=None optimization=Scaled-Dot-Product
21:23:42-224968 DEBUG Diffusers loading: path="D:\Stable Diffusion\Vladmandic\models\Stable-diffusion\Stable Video Diffusion\svd_xt.safetensors"
21:23:42-224968 INFO Autodetect: model="Stable Diffusion" class=StableDiffusionPipeline file="D:\Stable Diffusion\Vladmandic\models\Stable-diffusion\Stable Video Diffusion\svd_xt.safetensors" size=9117MB
config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4.52k/4.52k [00:00<?, ?B/s]
tokenizer_config.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 905/905 [00:00<?, ?B/s]
vocab.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 961k/961k [00:00<00:00, 15.4MB/s]
merges.txt: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 525k/525k [00:00<00:00, 33.6MB/s]
special_tokens_map.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 389/389 [00:00<?, ?B/s]
tokenizer.json: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2.22M/2.22M [00:00<00:00, 28.5MB/s]
21:23:44-912441 ERROR Diffusers failed loading: model=D:\Stable Diffusion\Vladmandic\models\Stable-diffusion\Stable Video Diffusion\svd_xt.safetensors pipeline=Autodetect/NoneType Cannot load because
conv_in.weight expected shape tensor(..., device='meta', size=(320, 4, 3, 3)), but got torch.Size([320, 8, 3, 3]). If you want to instead overwrite randomly initialized weights, please
make sure to pass both `low_cpu_mem_usage=False` and `ignore_mismatched_sizes=True`. For more information, see also:
https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389 as an example.
21:23:44-928067 ERROR loading model=D:\Stable Diffusion\Vladmandic\models\Stable-diffusion\Stable Video Diffusion\svd_xt.safetensors pipeline=Autodetect/NoneType: ValueError
╭────────────────────────────────────────────────────────────────────────────────────── Traceback (most recent call last) ──────────────────────────────────────────────────────────────────────────────────────╮
│ D:\Stable Diffusion\Vladmandic\modules\sd_models.py:1043 in load_diffuser │
│ │
│ 1042 │ │ │ │ │ │ sd_hijack_accelerate.restore_accelerate() │
│ ❱ 1043 │ │ │ │ │ sd_model = pipeline.from_single_file(checkpoint_info.path, **diffusers_load_config) │
│ 1044 │ │ │ │ │ sd_model = patch_diffuser_config(sd_model, checkpoint_info.path) │
│ │
│ D:\Stable Diffusion\Vladmandic\venv\lib\site-packages\huggingface_hub\utils\_validators.py:118 in _inner_fn │
│ │
│ 117 │ │ │
│ ❱ 118 │ │ return fn(*args, **kwargs) │
│ 119 │
│ │
│ D:\Stable Diffusion\Vladmandic\venv\lib\site-packages\diffusers\loaders\single_file.py:289 in from_single_file │
│ │
│ 288 │ │ │ else: │
│ ❱ 289 │ │ │ │ components = build_sub_model_components( │
│ 290 │ │ │ │ │ init_kwargs, │
│ │
│ D:\Stable Diffusion\Vladmandic\venv\lib\site-packages\diffusers\loaders\single_file.py:61 in build_sub_model_components │
│ │
│ 60 │ │ │
│ ❱ 61 │ │ unet_components = create_diffusers_unet_model_from_ldm( │
│ 62 │ │ │ pipeline_class_name, │
│ │
│ D:\Stable Diffusion\Vladmandic\venv\lib\site-packages\diffusers\loaders\single_file_utils.py:1322 in create_diffusers_unet_model_from_ldm │
│ │
│ 1321 │ │ │
│ ❱ 1322 │ │ unexpected_keys = load_model_dict_into_meta(unet, diffusers_format_unet_checkpoint, dtype=torch_dtype) │
│ 1323 │ │ if unet._keys_to_ignore_on_load_unexpected is not None: │
│ │
│ D:\Stable Diffusion\Vladmandic\venv\lib\site-packages\diffusers\models\modeling_utils.py:152 in load_model_dict_into_meta │
│ │
│ 151 │ │ │ model_name_or_path_str = f"{model_name_or_path} " if model_name_or_path is not None else "" │
│ ❱ 152 │ │ │ raise ValueError( │
│ 153 │ │ │ │ f"Cannot load {model_name_or_path_str}because {param_name} expected shape {empty_state_dict[param_name]}, but got {param.shape}. If you want to instead overwrite randomly initialized │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
ValueError: Cannot load because conv_in.weight expected shape tensor(..., device='meta', size=(320, 4, 3, 3)), but got torch.Size([320, 8, 3, 3]). If you want to instead overwrite randomly initialized weights, please make sure to pass both `low_cpu_mem_usage=False` and `ignore_mismatched_sizes=True`. For more information, see also: https://github.com/huggingface/diffusers/issues/1619#issuecomment-1345604389 as an example.
21:23:45-256203 DEBUG Script callback init time: image_browser.py:ui_tabs=0.53 system-info.py:app_started=0.09 task_scheduler.py:app_started=0.37
Backend
Diffusers
Branch
Master
Model
Other
Acknowledgements
- [X] I have read the above and searched for existing issues
- [X] I confirm that this is classified correctly and its not an extension issue
