Skip to content

Conversation

@Zehong-Ma
Copy link

We sincerely appreciate your excellent work on Wan2.2! 🙌
In this PR, we integrate our MagCache into the Wan2.2 framework. MagCache is a training-free caching strategy to accelerate diffusion models.

🌟 Highlights

  • 1.5-2× speedup on a single NVIDIA L20 GPU compared to the baseline.

  • Performance is achieved with negligible quality degradation.

  • MagCache is an enhanced alternative to TeaCache, providing better runtime efficiency while maintaining compatibility and minimal code changes.

The following are the comparisons conducted on a single L20 GPU. The left is the original video, while the right is the video generated with our MagCache.

TI2V_5B_t2v_magcache.mp4
TI2V_5B_i2v_magcache.mp4
T2V_A14B_magcache.mp4
I2V_A14B_magcache.mp4

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant