modelscope / modelscope/DiffSynth-Studio
Wan2.2 TI2V 的VAE compression ratio
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
Wan2.2 TI2V 的VAE compression ratio=4*16*16，應該跟Wan2.2 I2V的VAE compression ratio=4*8*8不一樣，兩者的VAE架構不一樣，可是為什麼都是用wan_video_vae.py同一份code
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 with diffsynth/models/wan_video_vae.py around line 1058 and compare the Wan2.2 TI2V and I2V VAE compression-ratio handling. Check whether the shared implementation matches the two stated architectures and ratios. Done means either correcting the handling or documenting why the shared code is intentional.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100