HeaderTooLarge

[Starzilla29]

when I run the scripts I get this funny error:

/mnt/Samsung980Pro/WORK/AI/arch/magic-animate/magicanimate/pipelines/pipeline_animation.py:43: FutureWarning: Importing `DiffusionPipeline` or `ImagePipelineOutput` from diffusers.pipeline_utils is deprecated. Please import from diffusers.pipelines.pipeline_utils instead.
  from diffusers.pipeline_utils import DiffusionPipeline
Traceback (most recent call last):
  File "/mnt/Samsung980Pro/arch_linux_software/anaconda3/envs/manimate/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/mnt/Samsung980Pro/arch_linux_software/anaconda3/envs/manimate/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/mnt/Samsung980Pro/WORK/AI/arch/magic-animate/magicanimate/pipelines/animation.py", line 282, in <module>
    run(args)
  File "/mnt/Samsung980Pro/WORK/AI/arch/magic-animate/magicanimate/pipelines/animation.py", line 271, in run
    main(args)
  File "/mnt/Samsung980Pro/WORK/AI/arch/magic-animate/magicanimate/pipelines/animation.py", line 76, in main
    text_encoder = CLIPTextModel.from_pretrained(config.pretrained_model_path, subfolder="text_encoder")
  File "/mnt/Samsung980Pro/arch_linux_software/anaconda3/envs/manimate/lib/python3.8/site-packages/transformers/modeling_utils.py", line 2805, in from_pretrained
    state_dict = load_state_dict(resolved_archive_file)
  File "/mnt/Samsung980Pro/arch_linux_software/anaconda3/envs/manimate/lib/python3.8/site-packages/transformers/modeling_utils.py", line 458, in load_state_dict
    with safe_open(checkpoint_file, framework="pt") as f:
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

Which seems to me like a problem with the hierarchy of models, however, with git cloning the models directly from hugging face, this seems to match... I don't see the issue here:

├── MagicAnimate
│   ├── appearance_encoder
│   │   ├── config.json
│   │   └── diffusion_pytorch_model.safetensors
│   ├── densepose_controlnet
│   │   ├── config.json
│   │   └── diffusion_pytorch_model.safetensors
│   ├── README.md
│   └── temporal_attention
│       └── temporal_attention.ckpt
├── sd-vae-ft-mse
│   ├── config.json
│   ├── diffusion_pytorch_model.bin
│   ├── diffusion_pytorch_model.safetensors
│   └── README.md
└── stable-diffusion-v1-5
    ├── feature_extractor
    │   └── preprocessor_config.json
    ├── model_index.json
    ├── README.md
    ├── safety_checker
    │   ├── config.json
    │   ├── model.fp16.safetensors
    │   ├── model.safetensors
    │   ├── pytorch_model.bin
    │   └── pytorch_model.fp16.bin
    ├── scheduler
    │   └── scheduler_config.json
    ├── text_encoder
    │   ├── config.json
    │   ├── model.fp16.safetensors
    │   ├── model.safetensors
    │   ├── pytorch_model.bin
    │   └── pytorch_model.fp16.bin
    ├── tokenizer
    │   ├── merges.txt
    │   ├── special_tokens_map.json
    │   ├── tokenizer_config.json
    │   └── vocab.json
    ├── unet
    │   ├── config.json
    │   ├── diffusion_pytorch_model.bin
    │   ├── diffusion_pytorch_model.fp16.bin
    │   ├── diffusion_pytorch_model.fp16.safetensors
    │   ├── diffusion_pytorch_model.non_ema.bin
    │   ├── diffusion_pytorch_model.non_ema.safetensors
    │   └── diffusion_pytorch_model.safetensors
    ├── v1-5-pruned.ckpt
    ├── v1-5-pruned-emaonly.ckpt
    ├── v1-5-pruned-emaonly.safetensors
    ├── v1-5-pruned.safetensors
    ├── v1-inference.yaml
    └── vae
        ├── config.json
        ├── diffusion_pytorch_model.bin
        ├── diffusion_pytorch_model.fp16.bin
        ├── diffusion_pytorch_model.fp16.safetensors
        └── diffusion_pytorch_model.safetensors

[huifly]

download stable-diffusion-v1-5/text_encoder/model.safetensors, not pytorch_model.bin

[AshokBatakala]

After cloning with “git lfs clone,” remember to use “git lfs pull” to download the weights.