My TG Channel - <a target="_blank" rel="ugc" href="https://t.me/StefanFalkokAI">https://t.me/StefanFalkokAI</a>My TG Chat - <a target="_blank" rel="ugc" href="https://t.me/+y4R5JybDZcFjMjFi">https://t.me/+y4R5JybDZcFjMjFi</a>My ComfyUI Build - <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/StefanFalkok/ComfyUI_portable_torch_2.10.0_cu130_cp313_sageattention_triton/tree/main">https://huggingface.co/datasets/StefanFalkok/ComfyUI_portable_torch_2.10.0_cu130_cp313_sageattention_triton/tree/main</a>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 DETAILSI have included workflow with wan 2.2 T2I with some loras.You need to have Wan 2.2 model low noise (<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main">https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main</a>), clip (<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp16.safetensors">https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp16.safetensors</a>) and vae (wan 2.1 vae)GGUF - <a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/LowNoise">https://huggingface.co/QuantStack/Wan2.2-T2V-A14B-GGUF/tree/main/LowNoise</a>Also I have included Loras from <a target="_blank" rel="ugc" href="https://civarchive.com/models/1832621/dslr-photovideo-wan-2122-low-noise?modelVersionId=2073884">https://civarchive.com/models/1832621/dslr-photovideo-wan-2122-low-noise?modelVersionId=2073884</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Wan2.2-Lightning/blob/main/Wan2.2-T2V-A14B-4steps-lora-250928/low_noise_model.safetensors">https://huggingface.co/lightx2v/Wan2.2-Lightning/blob/main/Wan2.2-T2V-A14B-4steps-lora-250928/low_noise_model.safetensors</a> for better generation. Also i recomend use loras <a target="_blank" rel="ugc" href="https://civarchive.com/models/1822984?modelVersionId=2180477">https://civarchive.com/models/1822984?modelVersionId=2180477</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/1662740?modelVersionId=2066914">https://civarchive.com/models/1662740?modelVersionId=2066914</a>I recommend generate images at least 540p, but for better results generate in 720pLeave comments if you have trouble or you found the problem with workflows

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

wan22T2ILowNoiseOnlyTextTo_v21InstagirlLora.zip

v2.1 (instagirl lora)

v4.3 (Lora Manager)

v4.2 (fixed MultiGPU)

v4.1 (fix resolut.update)

v4.0 (GGUF)

v3.0 (much faster gen.)

v2.0

v1.1

v1.0

Files with SHA256: 1d26b13109908da78f85d1037bb095eb1a00321f949f6f77dad3ddf1e6b19e3e