mrfakename
mrfakename
Does this code still use the official DiT implementation which is NC-licensed?
Thanks for changing it @kabachuha! Unfortunately there's still > The service is a research preview intended for non-commercial use only. See [LICENSE](https://github.com/PKU-YuanGroup/Open-Sora-Plan/blob/main/LICENSE) for details. in the README, would you mind...
cc @LinB203
Hi, is there any update on this? Would love to have this merged!
Any chance it could be permissively licensed?
Hi, if there are plans to reimplement the codebase should this issue be reopened?
@claydegruchy please check to make sure it's actually running on the gpu. I ran into this issue and realized I was using a version of torch that didn't support ROCm....
That would be nice. I was wondering if it would be possible to use chunking, and have previous chunks as context, to make the speech sound natural with different speakers....