This guide demonstrates how to generate videos with first and last frames using Wan2.1 Video in ComfyUI
ComfyUI/models/diffusion_models/
directory.
If you need other t2v precision versions, please visit here to download them.
Load Diffusion Model
node has loaded the wan2.1_t2v_1.3B_fp16.safetensors
modelLoad CLIP
node has loaded the umt5_xxl_fp8_e4m3fn_scaled.safetensors
modelLoad VAE
node has loaded the wan_2.1_vae.safetensors
modelEmptyHunyuanLatentVideo
node if neededCLIP Text Encoder
node at number 5
Run
button or use the shortcut Ctrl(cmd) + Enter
to execute the video generationComfyUI/models/diffusion_models/
directory.
Load Diffusion Model
node has loaded the wan2.1_i2v_480p_14B_fp16.safetensors
modelLoad CLIP
node has loaded the umt5_xxl_fp8_e4m3fn_scaled.safetensors
modelLoad VAE
node has loaded the wan_2.1_vae.safetensors
modelLoad CLIP Vision
node has loaded the clip_vision_h.safetensors
modelLoad Image
nodeCLIP Text Encoder
nodeWanImageToVideo
node if neededRun
button or use the shortcut Ctrl(cmd) + Enter
to execute the video generationComfyUI/models/diffusion_models/
directory.
Load Diffusion Model
node has loaded the wan2.1_i2v_720p_14B_fp16.safetensors
modelLoad CLIP
node has loaded the umt5_xxl_fp8_e4m3fn_scaled.safetensors
modelLoad VAE
node has loaded the wan_2.1_vae.safetensors
modelLoad CLIP Vision
node has loaded the clip_vision_h.safetensors
modelLoad Image
nodeCLIP Text Encoder
nodeWanImageToVideo
node if neededRun
button or use the shortcut Ctrl(cmd) + Enter
to execute the video generation