Wan 2.2 Long Video with 10 Steps Model Workflows (t2v, i2v, flf2v, up to 30 seconds) with MultiGPU + SageAttention + GGUF + Audio

https://huggingface.co/datasets/StefanFalkok/ComfyUI_portable_torch_2.9.1_cu130_cp313_sageattention_triton, also u need download and install CUDA 13.0 (https://developer.nvidia.com/cuda-13-0-0-download-archive) and VS Code (https://visualstudio.microsoft.com/downloads/)

My TG Channel - https://t.me/StefanFalkokAI

My TG Chat - https://t.me/+y4R5JybDZcFjMjFi

Hi! I introduce my long video workflows with Wan 2.2 generation video for ComfyUI.

I have included 6 workflows such as t2v, i2v,flf2v (firstlastframe) and 2 workflows with mmaudio and hunyuanvideofoley audio

Recomend resolutions: from 480p to 720p

You need to have Wan 2.2 10 steps models models (https://huggingface.co/StefanFalkok/Wan_2.2_10steps/tree/main), if you need - GGUF version (https://huggingface.co/StefanFalkok/Wan_2.2_10steps_GGUF/tree/main), clip (https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-bf16.safetensors) and vae (wan 2.1 vae)

All the details described in my workflows. Good look with generation!

Leave comments if you have trouble or you found the problem with workflows