Fixes Animate Replace Bug. #152
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(venv) mike@Alexandra:/project/video/Wan2.2$ python ./wan/modules/animate/preprocess/preprocess_data.py --ckpt_path ./Wan2.2-Animate-14B/process_checkpoint/ --video_path ./source/source.mp4 --refer_path ./source/person.png --save_path ./source/progress/ --resolution_area 1280 720 --iterations 3 --k 7 --w_len 1 --h_len 1 --replace_flag
{'ckpt_path': './Wan2.2-Animate-14B/process_checkpoint/', 'video_path': './source/source.mp4', 'refer_path': './source/person.png', 'save_path': './source/progress/', 'resolution_area': [1280, 720], 'fps': 30, 'replace_flag': True, 'retarget_flag': False, 'use_flux': False, 'iterations': 3, 'k': 7, 'w_len': 1, 'h_len': 1}
frame_num: 2646
video_fps: 30.0
fps: 30
target_num: 2646
2025-09-19 08:28:13.438 | INFO | process_pipepline:__call__:67 - Processing pose meta
2025-09-19 08:29:23.335 | INFO | process_pipepline:__call__:82 - Processing reference image: ./source/fabio.png
2025-09-19 08:29:23.352 | INFO | process_pipepline:__call__:89 - Processing template video: ./source/cousin.mp4
video frame: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 400/400 [00:07<00:00, 50.11it/s]
Traceback (most recent call last):
File "/project/video/Wan2.2/./wan/modules/animate/preprocess/preprocess_data.py", line 109, in <module>
process_pipeline(video_path=args.video_path,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/project/video/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 97, in __call__
masks = self.get_mask(frames, 400, tpl_pose_metas)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/project/video/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 319, in get_mask
self.predictor.reset_state(inference_state)
File "/project/video/.venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/project/video/.venv/lib/python3.11/site-packages/sam2/sam2_video_predictor.py", line 678, in reset_state
self._reset_tracking_results(inference_state)
File "/project/video/.venv/lib/python3.11/site-packages/sam2/sam2_video_predictor.py", line 701, in _reset_tracking_results
for v in inference_state["frames_tracked_per_obj"].values():
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^
KeyError: 'frames_tracked_per_obj'
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
(venv) mike@Alexandra:/project/video/Wan2.2$ python ./wan/modules/animate/preprocess/preprocess_data.py --ckpt_path ./Wan2.2-Animate-14B/process_checkpoint/ --video_path ./source/source.mp4 --refer_path ./source/person.png --save_path ./source/progress/ --resolution_area 1280 720 --iterations 3 --k 7 --w_len 1 --h_len 1 --replace_flag
{'ckpt_path': './Wan2.2-Animate-14B/process_checkpoint/', 'video_path': './source/source.mp4', 'refer_path': './source/person.png', 'save_path': './source/progress/', 'resolution_area': [1280, 720], 'fps': 30, 'replace_flag': True, 'retarget_flag': False, 'use_flux': False, 'iterations': 3, 'k': 7, 'w_len': 1, 'h_len': 1}
frame_num: 2646
video_fps: 30.0
fps: 30
target_num: 2646
2025-09-19 08:28:13.438 | INFO | process_pipepline:call:67 - Processing pose meta
2025-09-19 08:29:23.335 | INFO | process_pipepline:call:82 - Processing reference image: ./source/person.png
2025-09-19 08:29:23.352 | INFO | process_pipepline:call:89 - Processing template video: ./source/source.mp4
video frame: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 400/400 [00:07<00:00, 50.11it/s]
Traceback (most recent call last):
File "/project/video/Wan2.2/./wan/modules/animate/preprocess/preprocess_data.py", line 109, in
process_pipeline(video_path=args.video_path,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/project/video/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 97, in call
masks = self.get_mask(frames, 400, tpl_pose_metas)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/project/video/Wan2.2/wan/modules/animate/preprocess/process_pipepline.py", line 319, in get_mask
self.predictor.reset_state(inference_state)
File "/project/video/.venv/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/project/video/.venv/lib/python3.11/site-packages/sam2/sam2_video_predictor.py", line 678, in reset_state
self._reset_tracking_results(inference_state)
File "/project/video/.venv/lib/python3.11/site-packages/sam2/sam2_video_predictor.py", line 701, in _reset_tracking_results
for v in inference_state["frames_tracked_per_obj"].values():
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^
KeyError: 'frames_tracked_per_obj'