Got RuntimeError:: element 0 of tensors does not require grad and does not have a grad_fn

[baomuhedao]

video to video translation...
processing batch [1/7] with 8 frames
FutureWarning: _encode_prompt() is deprecated and it will be removed in a future version. Use encode_prompt() instead. Also, be aware that the output format changed from a concatenated tensor to a tuple.

0%| | 0/15 [00:00<?, ?it/s]
0%| | 0/15 [00:00<?, ?it/s]
!!! Exception during processing !!!
Traceback (most recent call last):
File "/data/comfy-ui/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/data/comfy-ui/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/comfy-ui/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/data/comfy-ui/custom_nodes/comfyui-cartoon-stylization/nodes.py", line 68, in stylize
FrescoService().stylize(video_file_path,output_dir,prompt)
File "/data/comfy-ui/custom_nodes/comfyui-cartoon-stylization/fresco_service.py", line 39, in stylize
keys = run_keyframe_translation(config)
File "/data/comfy-ui/custom_nodes/comfyui-cartoon-stylization/fresco/run_fresco.py", line 239, in run_keyframe_translation
latents = inference(pipe, controlnet, frescoProc,
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/data/comfy-ui/custom_nodes/comfyui-cartoon-stylization/fresco/src/pipe_FRESCO.py", line 202, in inference
noise_pred = pipe.unet(
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/data/comfy-ui/custom_nodes/comfyui-cartoon-stylization/fresco/src/diffusion_hacked.py", line 778, in forward
sample = optimize_feature(sample, flows, occs, correlation_matrix,
File "/data/comfy-ui/custom_nodes/comfyui-cartoon-stylization/fresco/src/diffusion_hacked.py", line 487, in optimize_feature
optimizer.step(closure)
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/optim/optimizer.py", line 373, in wrapper
out = func(*args, **kwargs)
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/optim/optimizer.py", line 76, in _use_grad
ret = func(self, *args, **kwargs)
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/optim/adam.py", line 143, in step
loss = closure()
File "/data/comfy-ui/custom_nodes/comfyui-cartoon-stylization/fresco/src/diffusion_hacked.py", line 480, in closure
loss.backward()
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/_tensor.py", line 492, in backward
torch.autograd.backward(
File "/data/comfy-ui/venv/lib/python3.10/site-packages/torch/autograd/init.py", line 251, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

[williamyang1991]

Do you use the suggested diffusers version (diffusers 0.19.3)?
My code didn't report the warning

FutureWarning: _encode_prompt() is deprecated and it will be removed in a future version. Use encode_prompt() instead. Also, be aware that the output format changed from a concatenated tensor to a tuple.