search

chaojie / ComfyUI-DragAnything

66 stars 6 forks source link

For the basic workflow, error: #3

Open feiding333 opened 5 months ago

feiding333 commented 5 months ago

Error occurred when executing DragAnythingRun: expected Tensor as element 0 in argument 0, but got NoneType File "/data/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/data/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/data/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/nodes.py", line 624, in run validation_control_images,ids_embedding,vis_images = get_condition(target_size=(height , width), File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/nodes.py", line 309, in get_condition keyframe_dift = extract_dift_feature(first_frame, dift_model=dift_model) File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/nodes.py", line 293, in extract_dift_feature dift_feature = dift_model.forward(img_tensor, prompt=prompt, up_ft_index=3,ensemble_size=8) File "/data/miniconda3/envs/env-novelai/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, **kwargs) File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/utils/dift_util.py", line 214, in forward prompt_embeds = self.pipe._encode_prompt( File "/data/miniconda3/envs/env-novelai/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py", line 308, in _encode_prompt prompt_embeds = torch.cat([prompt_embeds_tuple[1], prompt_embeds_tuple[0]])

taiyouZhang commented 4 months ago

me too, any ideas?

taiyouZhang commented 4 months ago

Error occurred when executing DragAnythingRun: expected Tensor as element 0 in argument 0, but got NoneType File "/data/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/data/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/data/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(*slice_dict(input_data_all, i))) File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/nodes.py", line 624, in run validation_control_images,ids_embedding,vis_images = get_condition(target_size=(height , width), File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/nodes.py", line 309, in get_condition keyframe_dift = extract_dift_feature(first_frame, dift_model=dift_model) File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/nodes.py", line 293, in extract_dift_feature dift_feature = dift_model.forward(img_tensor, prompt=prompt, up_ft_index=3,ensemble_size=8) File "/data/miniconda3/envs/env-novelai/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, **kwargs) File "/data/ComfyUI/custom_nodes/ComfyUI-DragAnything/utils/dift_util.py", line 214, in forward prompt_embeds = self.pipe._encode_prompt( File "/data/miniconda3/envs/env-novelai/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py", line 308, in _encode_prompt prompt_embeds = torch.cat([prompt_embeds_tuple[1], prompt_embeds_tuple[0]])

I check the source code and commit a fix. It works for me. https://github.com/chaojie/ComfyUI-DragAnything/pull/4