Skip to main content
Wan FLF2V (First-Last Frame Video Generation) is an open-source video generation model developed by the Alibaba Tongyi Wanxiang team. Its open-source license is Apache 2.0. Users only need to provide two images as the starting and ending frames, and the model automatically generates intermediate transition frames, outputting a logically coherent and naturally flowing 720p high-definition video. Core Technical Highlights
  1. Precise First-Last Frame Control: The matching rate of first and last frames reaches 98%, defining video boundaries through starting and ending scenes, intelligently filling intermediate dynamic changes to achieve scene transitions and object morphing effects.
  2. Stable and Smooth Video Generation: Using CLIP semantic features and cross-attention mechanisms, the video jitter rate is reduced by 37% compared to similar models, ensuring natural and smooth transitions.
  3. Multi-functional Creative Capabilities: Supports dynamic embedding of Chinese and English subtitles, generation of anime/realistic/fantasy and other styles, adapting to different creative needs.
  4. 720p HD Output: Directly generates 1280x720 resolution videos without post-processing, suitable for social media and commercial applications.
  5. Open-source Ecosystem Support: Model weights, code, and training framework are fully open-sourced, supporting deployment on mainstream AI platforms.
Technical Principles and Architecture
  1. DiT Architecture: Based on diffusion models and Diffusion Transformer architecture, combined with Full Attention mechanism to optimize spatiotemporal dependency modeling, ensuring video coherence.
  2. 3D Causal Variational Encoder: Wan-VAE technology compresses HD frames to 1/128 size while retaining subtle dynamic details, significantly reducing memory requirements.
  3. Three-stage Training Strategy: Starting from 480P resolution pre-training, gradually upgrading to 720P, balancing generation quality and computational efficiency through phased optimization.
Related Links
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 If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons: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

​
Wan2.1 FLF2V 720P ComfyUI Native Workflow Example

Since this model is trained on high-resolution images, using smaller sizes may not yield good results. In the example, we use a size of 720 * 1280, which may cause users with lower VRAM hard to run smoothly and will take a long time to generate. If needed, please adjust the video generation size for testing. A small generation size may not produce good output with this model, please notice that.
Update your ComfyUI to the latest version, then download and drag the workflow file into ComfyUI, or find “Wan2.1 FLF2V 720P” in the Template Library under Workflow → Browse Templates → Video. Wan2.1 FLF2V 720P Workflow Preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Wan2.1 FLF2V” in Template Library

Start Image: wan2.1_flf2v_720_f16_start_image.png

Starting frame for the video generation (LoadImage node 52). Download and use this image, or replace with your own.

End Image: wan2.1_flf2v_720_f16_end_image.png

Ending frame for the video generation (LoadImage node 72). Download and use this image, or replace with your own.

​
2. Manual Model Installation

All models involved in this guide can be found here. Diffusion Models : Choose one version based on your hardware

Diffusion Model: Wan2.1 FLF2V 14B FP16

wan2.1_flf2v_720p_14B_fp16.safetensors : Full precision, requires more VRAM. Place in ComfyUI/models/diffusion_models/

Diffusion Model: Wan2.1 FLF2V 14B FP8

wan2.1_flf2v_720p_14B_fp8_e4m3fn.safetensors : Quantized version, lower VRAM usage. Place in ComfyUI/models/diffusion_models/
If you have previously tried Wan Video related workflows, you may already have the following files.
Text Encoders : Choose one version

Text Encoder: UMT5 XXL FP16

umt5_xxl_fp16.safetensors : Full precision text encoder. Place in ComfyUI/models/text_encoders/

Text Encoder: UMT5 XXL FP8

umt5_xxl_fp8_e4m3fn_scaled.safetensors : Quantized text encoder. Place in ComfyUI/models/text_encoders/
VAE

VAE: Wan2.1 VAE

wan_2.1_vae.safetensors : Wan2.1 VAE for encoding/decoding. Place in ComfyUI/models/vae/
CLIP Vision

CLIP Vision: CLIP Vision H

clip_vision_h.safetensors : CLIP Vision encoder. Place in ComfyUI/models/clip_vision/
File Storage Location

​
3. Complete Workflow Execution Step by Step

Wan2.1 FLF2V 720P Native Workflow Steps
  1. Ensure the Load Diffusion Model node has loaded wan2.1_flf2v_720p_14B_fp16.safetensors or wan2.1_flf2v_720p_14B_fp8_e4m3fn.safetensors
  2. Ensure the Load CLIP node has loaded umt5_xxl_fp8_e4m3fn_scaled.safetensors
  3. Ensure the Load VAE node has loaded wan_2.1_vae.safetensors
  4. Ensure the Load CLIP Vision node has loaded clip_vision_h.safetensors
  5. Upload the starting frame to the Start_image node
  6. Upload the ending frame to the End_image node
  7. (Optional) Modify the positive and negative prompts, both Chinese and English are supported
  8. (Important) In WanFirstLastFrameToVideo we use 7201280 as default size.because it’s a 720P model, so using a small size will not yield good output. Please use size around 7201280 for good generation.
  9. Click the Run button, or use the shortcut Ctrl(cmd) + Enter to execute video generation