OSError: Error no file named diffusion_pytorch_model.fp16.bin found in directory

[laogu1027]

Which model should be placed?

svd_xt_1_1.safetensors in ComfyUI\models\diffusers is error

THX

[kijai]

It needs to be the diffusers version, so all this:

And in each folder the .json files, and the fp16 .safetensors file, for example the unet:

This should all be automatically done by the loader node, is that not working for you?

[laogu1027]

OKOK.Just connection problem. but useing your orignal workflow: retrieve_timesteps() takes from 1 to 4 positional arguments but 5 were given

[kijai]

OKOK.Just connection problem. but useing your orignal workflow: retrieve_timesteps() takes from 1 to 4 positional arguments but 5 were given

Need to update your diffusers version.

[xyff83]

这个报错撒意思？

[laogu1027]

Thank u,have done

[laogu1027]

网络问题，兄弟

[winniewlx]

Error occurred when executing DownloadAndLoadMimicMotionModel:

Error no file named pytorch_model.fp16.bin, model.fp16.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory C:\Users\30759\Desktop\AI\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\models\diffusers\stable-video-diffusion-img2vid-xt-1-1.

File "C:\Users\30759\Desktop\AI\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\30759\Desktop\AI\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\30759\Desktop\AI\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\30759\Desktop\AI\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-MimicMotionWrapper\nodes.py", line 134, in loadmodel self.image_encoder = CLIPVisionModelWithProjection.from_pretrained(svd_path, subfolder="image_encoder", variant="fp16", low_cpu_mem_usage=True).to(dtype).to(device).eval() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\30759\Desktop\AI\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\transformers\modeling_utils.py", line 3460, in from_pretrained raise EnvironmentError(