Timon Käch

The model is here: https://huggingface.co/wangfuyun/AnimateLCM

Thanks for the update! I'm very hyped for the image to video release. Great work! I was always looking for a low latency solution

I would also like to know how to increase the generated texture resolution automatically. +1

Maybe a combination of projecting and the generated will work good together for the front and the back?

I'm interested in this feature too! Thanks

Nice! Looking forward to it :)

Can you please upload Q5_K_M if you have time? This has a good tradeoff between quality and size

I also run into the same issue. I really hope this get's fixed soon as fp8 enables much less vram usage.

Does anyone know how this got implemented in other repos? Maybe we can look at their code and do it ourselve.

I also get the same error. Please help. Python 3.10, Cuda 12.1, Ubuntu 22.04