Skip to content

Workflows Premium Workflows Templates Guides Work with us

Wan 2.2 text to image

Use Wan 2.2 high- and low-noise models to generate a still image.

Wan 2.2Image

Wan 2.2 · text-to-image · ComfyUI

Workflow preview

Wan 2.2 text to image workflow overview showing node groups and connections

44 KB · JSON file

Need a hand? Load your workflow or troubleshoot your Runpod setup.

Replace prompt placeholders and supply your own input images, video or audio before running.

Models to download

Check the required model files before running this workflow.

4xLSDIR.pth (ComfyUI/models/upscale_models)Model source for 4xLSDIR.pth (ComfyUI/models/upscale_models)
umt5_xxl_fp8_e4m3fn_scaled.safetensors (ComfyUI/models/text_encoders)Model source for umt5_xxl_fp8_e4m3fn_scaled.safetensors (ComfyUI/models/text_encoders)
wan_2.1_vae.safetensors (ComfyUI/models/vae)Model source for wan_2.1_vae.safetensors (ComfyUI/models/vae)
wan2.2_t2v_high_noise_14B_fp16.safetensors (ComfyUI/models/diffusion_models)Model source for wan2.2_t2v_high_noise_14B_fp16.safetensors (ComfyUI/models/diffusion_models)
wan2.2_t2v_low_noise_14B_fp16.safetensors (ComfyUI/models/diffusion_models)Model source for wan2.2_t2v_low_noise_14B_fp16.safetensors (ComfyUI/models/diffusion_models)