Skip to main content
Wan2.2-Fun-Inp is a start-end frame controlled video generation model launched by Alibaba PAI team. It supports inputting start and end frame images to generate intermediate transition videos, providing creators with greater creative control. The model is released under the Apache 2.0 license and supports commercial use. Key Features:
  • Start-End Frame Control: Supports inputting start and end frame images to generate intermediate transition videos, enhancing video coherence and creative freedom
  • High-Quality Video Generation: Based on the Wan2.2 architecture, outputs film-level quality videos
  • Multi-Resolution Support: Supports generating videos at 512x512, 768x768, 1024x1024 and other resolutions to suit different scenarios
Model Version:
  • 14B High-Performance Version: Model size exceeds 32GB, with better results but requires high VRAM
Below are the relevant model weights and code repositories:

​
ComfyOrg Wan2.2 Fun InP & Control Youtube Live Stream Replay

​
Wan2.2 Fun Inp Start-End Frame Video Generation Workflow Example

Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup
This workflow provides two versions:
  1. A version using Wan2.2-Lightning 4-step LoRA from lightx2v for accelerated video generation
  2. A fp8_scaled version without acceleration LoRA
Below are the test results using an RTX4090D 24GB VRAM GPU at 640x640 resolution with 81 frames Since the acceleration with LoRA is significant but the video dynamic is lost, the provided workflows enable the accelerated LoRA version by default. If you want to enable the other workflow, select it and use Ctrl+B to activate.

​
1. Download Workflow File

Please update your ComfyUI to the latest version, and find “Wan2.2 Fun Inp” under the menu Workflow -> Browse Templates -> Video to load the workflow. Or, after updating ComfyUI to the latest version, download the workflow below and drag it into ComfyUI to load. Wan2.2 Fun Inp workflow

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Wan2.2 Fun Inp” in Template Library
Use the following materials as the start and end frames Input materials

video_wan2_2_14B_fun_inpaint_start_image.png

Start frame for video generation. Download and use this image, or replace with your own.

video_wan2_2_14B_fun_inpaint_end_image.png

End frame for video generation. Download and use this image, or replace with your own.

​
2. Models

All models involved in this guide can be found here. Diffusion Models

High Noise 14B FP8 Scaled

wan2.2_fun_inpaint_high_noise_14B_fp8_scaled.safetensors: High noise diffusion model for start-end frame inpainting

Low Noise 14B FP8 Scaled

wan2.2_fun_inpaint_low_noise_14B_fp8_scaled.safetensors: Low noise diffusion model for start-end frame inpainting
Lightning LoRA (Optional, for acceleration)

Lightning 4-Step High Noise LoRA

wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors: 4-step acceleration LoRA for high noise model

Lightning 4-Step Low Noise LoRA

wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors: 4-step acceleration LoRA for low noise model
VAE

Wan2.1 VAE

wan_2.1_vae.safetensors: Wan2.1 VAE for encoding and decoding
Text Encoder

UMT5 XXL FP8 Scaled

umt5_xxl_fp8_e4m3fn_scaled.safetensors: Scaled FP8 text encoder

​
3. Workflow Guide

Workflow Step Image
This workflow uses LoRA. Please make sure the corresponding Diffusion model and LoRA are matched.
  1. High noise model and LoRA loading
    • Ensure the Load Diffusion Model node loads the wan2.2_fun_inpaint_high_noise_14B_fp8_scaled.safetensors model
    • Ensure the LoraLoaderModelOnly node loads the wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors
  2. Low noise model and LoRA loading
    • Ensure the Load Diffusion Model node loads the wan2.2_fun_inpaint_low_noise_14B_fp8_scaled.safetensors model
    • Ensure the LoraLoaderModelOnly node loads the wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors
  3. Ensure the Load CLIP node loads the umt5_xxl_fp8_e4m3fn_scaled.safetensors model
  4. Ensure the Load VAE node loads the wan_2.1_vae.safetensors model
  5. Upload the start and end frame images as materials
  6. Enter your prompt in the Prompt group
  7. Adjust the size and video length in the WanFunInpaintToVideo node
    • Adjust the width and height parameters. The default is 640. We set a smaller size, but you can modify it as needed.
    • Adjust the length, which is the total number of frames. The current workflow fps is 16. For example, if you want to generate a 5-second video, you should set it to 5*16 = 80.
  8. Click the Run button, or use the shortcut Ctrl(cmd) + Enter to execute video generation