Instructions to use Comfy-Org/HunyuanVideo_1.5_repackaged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/HunyuanVideo_1.5_repackaged with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
720p version of hunyuanvideo1.5_t2v_lightx2v lora
Is a 720p version of hunyuanvideo 1.5_t2v_lightx2v lora available in the future to reduce the time consumption of low-resolution or necessarily upsampling models? π
from my first tests it seems to work with 720p as well. But it's weird i can't find any other source for these on HF.
But there is Phr00t's AIO version of Hunyuan Video 1.5 which is very fast.
in general i rarely use it HV1.5 , it needs a LOT more prompt micromanaging than Wan2.2 and i'm lazy. While Wan is amazing at filling the gaps by itself in a usually sensible way. I guess that's whyHV1-5 it never got the massive support. But if you're willing to micromanage the prompt it can do interesting stuff.