I think it turned out slightly undercooked but 12 hours of training is 12 hours of training so here it is.
Trained on 1024 resolution and double blocks.
If you enjoy my work please consider leaving a like or a review. Pics of your work are also appreciated :)
Description
FAQ
Comments (8)
Great Lora! Did you use musubi?
Diffusion pipe
@JaneB linux or on windows via wsl ?
@NoArtifact I have done it both ways
@JaneB ok, I have yet to motivate myself to try (i'm so bad with installing pythong script and stuff) but I might seeing how good it can turn out, thanks for the reply
@NoArtifact https://civitai.com/articles/10547/train-lora-for-hunyuan-video-using-diffusion-pipe-interface-with-docker-runpod-and-vastai There is a link there for an docker images for runpod with everything installed
@JaneB thanks for the link, It seems even more complicated than the other one (which apparently don't involve docker) but i'll keep an eye on it if I can't manage to run the other way
😍 👍🏻