Type | Workflows |
Stats | 863 0 |
Reviews | (38) |
Published | Mar 9, 2025 |
Base Model | |
Hash | AutoV2 82C981E746 |
Recently, HyVideo released an official I2V model along with a quantized version, so I updated the I2V workflow as well. This is a basic process using GGUF, nothing special.
Since I have 12GB of VRAM, I used Q4, but if your VRAM is sufficient, I recommend using Q5 or higher. For better quality, increase the number of steps and resolution.
PS:Wavespeed/Teacache is not required. If you can't use it, disable the node (CTRL+B).
use note:
1、GGUF download link
2、Other model download link
llava_llama3_vision>..\models\clip_vision\
gguf>..\models\unet
skyreel smooth lora download link
hunyuan video fast lora download link
If you like this model, please 👍 it and leave a review! Also, feel free to give me a ⚡, it would be greatly appreciated.If you don't like it, still let me know why so that I can improve!
※ I using Forge or Comyfui to gen. If your results don't match mine exactly, this may explain why.My LORA may not work on certain checkpoints. If that's the case, please switch to a different checkpoint.