This guide demonstrates how to use Wan2.1 Fun InP in ComfyUI to generate videos with first and last frame control
Wan-Fun InP is an open-source video generation model released by Alibaba, part of the Wan2.1-Fun series, focusing on generating videos from images with first and last frame control.
Key features:
Model versions:
Below are the relevant model weights and code repositories:
Currently, ComfyUI natively supports the Wan2.1 Fun InP model. Before starting this tutorial, please update your ComfyUI to ensure your version is after this commit.
If you find missing nodes when loading the workflow file below, it may be due to the following situations:
Please make sure you have successfully updated ComfyUI to the latest Development (Nightly) version. See: How to Update ComfyUI section to learn how to update ComfyUI.
Download the image below and drag it into ComfyUI to load the workflow:
If automatic model downloading is ineffective, please download the models manually and save them to the corresponding folders.
The following models can be found at Wan_2.1_ComfyUI_repackaged and Wan2.1-Fun
Diffusion models - choose 1.3B or 14B. The 14B version has a larger file size (32GB) and higher VRAM requirements:
Wan2.1-Fun-14B-InP.safetensors
after downloadingText encoders - choose one of the following models (fp16 precision has a larger size and higher performance requirements):
VAE
CLIP Vision
File storage location:
Load Diffusion Model
node has loaded wan2.1_fun_inp_1.3B_bf16.safetensors
Load CLIP
node has loaded umt5_xxl_fp8_e4m3fn_scaled.safetensors
Load VAE
node has loaded wan_2.1_vae.safetensors
Load CLIP Vision
node has loaded clip_vision_h.safetensors
Load Image
node (renamed to Start_image
)Load Image
nodeWanFunInpaintToVideo
, avoiding overly large dimensionsRun
button or use the shortcut Ctrl(cmd) + Enter
to execute video generationPlease make sure to use the correct model, as wan2.1_fun_inp_1.3B_bf16.safetensors
and wan2.1_fun_control_1.3B_bf16.safetensors
are stored in the same folder and have very similar names. Ensure you’re using the right model.