search

Tencent / MimicMotion

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
https://tencent.github.io/MimicMotion/
Other
1.92k stars 162 forks source link

Error occurred when executing MimicMotionSampler: "compute_index_ranges_weights" not implemented for 'Half' #81

Open Killydon opened 2 months ago

Killydon commented 2 months ago

Error occurred when executing MimicMotionSampler: "compute_index_ranges_weights" not implemented for 'Half' File "/Users/ddass/AI/ComfyUI/execution.py", line 317, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/Users/ddass/AI/ComfyUI/execution.py", line 192, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/Users/ddass/AI/ComfyUI/execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "/Users/ddass/AI/ComfyUI/execution.py", line 158, in process_inputs results.append(getattr(obj, func)(*inputs)) File "/Users/ddass/AI/ComfyUI/custom_nodes/ComfyUI-MimicMotionWrapper/nodes.py", line 300, in process frames = pipeline( File "/Users/ddass/opt/anaconda3/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, *kwargs) File "/Users/ddass/AI/ComfyUI/custom_nodes/ComfyUI-MimicMotionWrapper/mimicmotion/pipelines/pipeline_mimicmotion.py", line 521, in call image_embeddings = self._encode_image(image, device, num_videos_per_prompt, self.do_classifier_free_guidance, image_embed_strength=image_embed_strength) File "/Users/ddass/AI/ComfyUI/custom_nodes/ComfyUI-MimicMotionWrapper/mimicmotion/pipelines/pipeline_mimicmotion.py", line 152, in _encode_image image = clip_preprocess(image.clone(), 224) File "/Users/ddass/AI/ComfyUI/comfy/clip_vision.py", line 25, in clip_preprocess image = torch.nn.functional.interpolate(image, size=(round(scale image.shape[2]), round(scale * image.shape[3])), mode="bicubic", antialias=True) File "/Users/ddass/opt/anaconda3/lib/python3.9/site-packages/torch/nn/functional.py", line 4072, in interpolate return torch._C._nn._upsample_bicubic2d_aa(input, output_size, align_corners, scale_factors)

Anyone have a solution to this error?

TankLin2017 commented 2 months ago

Error occurred when executing MimicMotionSampler:

"compute_indices_weights_aa" not implemented for 'Half'

File "F:\sd-comfyui_v1.0\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\sd-comfyui_v1.0\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 "F:\sd-comfyui_v1.0\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\sd-comfyui_v1.0\ComfyUI\custom_nodes\ComfyUI-MimicMotionWrapper\nodes.py", line 300, in process frames = pipeline( ^^^^^^^^^ File "F:\sd-comfyui_v1.0\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "F:\sd-comfyui_v1.0\ComfyUI\custom_nodes\ComfyUI-MimicMotionWrapper\mimicmotion\pipelines\pipeline_mimicmotion.py", line 521, in call image_embeddings = self._encode_image(image, device, num_videos_per_prompt, self.do_classifier_free_guidance, image_embed_strength=image_embed_strength) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\sd-comfyui_v1.0\ComfyUI\custom_nodes\ComfyUI-MimicMotionWrapper\mimicmotion\pipelines\pipeline_mimicmotion.py", line 152, in _encode_image image = clip_preprocess(image.clone(), 224) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\sd-comfyui_v1.0\ComfyUI\comfy\clip_vision.py", line 25, in clip_preprocess image = torch.nn.functional.interpolate(image, size=(round(scale image.shape[2]), round(scale * image.shape[3])), mode="bicubic", antialias=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\sd-comfyui_v1.0\python_embeded\Lib\site-packages\torch\nn\functional.py", line 4045, in interpolate return torch._C._nn._upsample_bicubic2d_aa(input, output_size, align_corners, scale_factors) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

the same, who can help us???

TankLin2017 commented 2 months ago

image I set the precision fp16, and it bug me Error occurred when executing MimicMotionSampler: "compute_indices_weights_aa" not implemented for 'Half'.