Currently in ALPHA. A new dataset is being built to retrain with better fidelity using the strategy outlined in this guide: https://civitai.com/articles/11942/training-a-wan-or-hunyuan-lora-the-right-way
This LoRA should play well with other LoRAs without needing to mess with strength much.
All videos contain metadata required to generate them.
Final version
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.