Hello everyone, this is the latest Wan2.2 VACE model, the KJ version workflow. It includes features such as start-end image prediction, video control weight, and video character replacement. Before use, you need to download the KJ quantized VACE model. I will list the specific model details and usage methods in the text below.

Models to download
1. 2.2Fun vace
https://hf mirror.com/Kijai/WanVideo_comfy/tree/main/Fun/VACE
Folder location: models\diffusion_models
2. Lightning_T2V V1.1 A14B 4Step
https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Wan22 Lightning
3. Wan2.2_T2V_fp8 HIGH and LOW
https://hf mirror.com/Kijai/WanVideo_comfy_fp8_scaled/tree/main/T2V
4. Ensure sageattn can be used normally

Note: For local operation, if the video memory is below 16G and you encounter memory overflow issues, you can increase blocks to swap. It is recommended to increase it to 39.