Many people have reported that the teeth and lips generated by LatentSync 1.5 are blurry. To address this issue, we trained LatentSync 1.6 on 512 x 512 resolution videos.
Notably, we did not make any changes to the model structure or training strategy; the only modification was upgrading the training dataset to 512 x 512 videos. Therefore, the current code is compatible with both LatentSync 1.5 and 1.6. To switch between versions, you only need to load the corresponding checkpoint and modify the
resolution
parameter in the U-Net config file.
You can view the
demo
in LatentSync's official GitHub repo.
Runs of ByteDance LatentSync-1.6 on huggingface.co
204.7K
Total runs
2.7K
24-hour runs
766
3-day runs
15.6K
7-day runs
96.5K
30-day runs
More Information About LatentSync-1.6 huggingface.co Model
LatentSync-1.6 huggingface.co is an AI model on huggingface.co that provides LatentSync-1.6's model effect (), which can be used instantly with this ByteDance LatentSync-1.6 model. huggingface.co supports a free trial of the LatentSync-1.6 model, and also provides paid use of the LatentSync-1.6. Support call LatentSync-1.6 model through api, including Node.js, Python, http.
LatentSync-1.6 huggingface.co is an online trial and call api platform, which integrates LatentSync-1.6's modeling effects, including api services, and provides a free online trial of LatentSync-1.6, you can try LatentSync-1.6 online for free by clicking the link below.
ByteDance LatentSync-1.6 online free url in huggingface.co:
LatentSync-1.6 is an open source model from GitHub that offers a free installation service, and any user can find LatentSync-1.6 on GitHub to install. At the same time, huggingface.co provides the effect of LatentSync-1.6 install, users can directly use LatentSync-1.6 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.