OpenImagingLab / OpenImagingLab/FlashVSR
Reproduction issue of stage 2.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.9k
- Forks
- 152
- PR merge metrics
- No merged PRs in 30d
Description
Hi, authors of FlashVSR. Thanks for contributing so excellent work for the community.
But I still meet some problems when using it on some extremely bad cases, So I would like to fine-tune it.
And thus I am trying to reproduce the training code, but I got some problems during reproducing stage 2, and I hope you can share some details about that:
- LR_proj module is converted into Causal one for only inference or both inference and training?
- generate_draft_block_mask in wan_video_dit.py is only for inference? As it can be derivable. Do you use other mask strategy during your training?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading wan_video_dit.py and tracing LR_proj and generate_draft_block_mask through the stage 2 training and inference paths. Compare the available reproduction code with the reported questions; done would mean establishing the training behavior and documenting the missing details needed to reproduce stage 2.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100