WAN 2.2 T2I Low Noise Only (Text to Image) With SageAttention + BlockSwap + NSFW

Hi! I introduce my working workflows with Wan 2.2 generationg video for ComfyUI.

I RECOMMEND ADJUSTING STRENGTH OF LIGHTNING LORA FROM 0.5 TO 1 TO AVOID OVER MANY DETAILS

I have included workflow with wan 2.2 T2I with some loras.

You need to have Wan 2.2 model low noise (https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main), clip (https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-bf16.safetensors) and vae (wan 2.1 vae)

GGUF - https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/LowNoise

Also I have included Loras from /model/1832621/dslr-photovideo-wan-2122-low-noise?modelVersionId=2073884 and https://huggingface.co/lightx2v/Wan2.2-Lightning/blob/main/Wan2.2-T2V-A14B-4steps-lora-250928/low_noise_model.safetensors for better generation. Also i recomend use loras /model/1822984?modelVersionId=2180477 and /model/1662740?modelVersionId=2066914

Also you need to have Sageattention 2.2.0 with Triton (https://huggingface.co/Kijai/PrecompiledWheels/tree/main) and Torch 2.7.0+ for faster generation (https://github.com/pytorch/pytorch/releases), also u need download and install CUDA 12.8 (https://developer.nvidia.com/cuda-12-8-0-download-archive) and VS Code (https://visualstudio.microsoft.com/downloads/)

Instruction how to install Sageattention (1.0.6, how to install sageattention 2.2.0 - rename .whl file to .zip and put folders from .zip to ComfyUI\python_embeded\Lib\site-packages)

I recommend generate images at least 540p, but for better results generate in 720p

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