Kohya has released a Lora training script for the Hunyuan Video model. It will allow 16GB VRAM cards to train video Lora using only image input.
And support for image training video models lora
Civitai There is now a Lora released by fok3827, which also supports NSFW.origin of the universeIs there a possibility of turning the SD into a video model?
Lora address and training tutorial below
Training script visualization interface
Since there is no GUI and there is a lot of work to set up. The gods have created a package with all the repositories, models, Python and GUI. See the video below:video tutorial
A version has now been uploaded to Google Drive without models/ckpts.
Please check the following links.
https://drive.google.com/file/d/1JkQMPBaNf83GlHvQrvdWULdrPdItTQCJ/view?usp=sharing
Please follow the link below to download ckpts separately and place the ckpts folder in . /models!
https://github.com/Tencent/HunyuanVideo/blob/main/ckpts/README.md
Will Hunyuan Video (HV) become a STABLE diffusion in video generation?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil