WAN2.1 Start and End Frame Generation
Upload two images to complete the middle segments

Workspace

1. Upload **start frame image 1** and **end frame image 2**

2. Enter prompt words (optional, minimal impact)

3. Video duration
You can input 21, 41, 61, 81; other frames may encounter errors due to length issues

4. Adjust animation amplitude
The larger the value, the greater the amplitude
5. Simply generate

Notes ⚠️

1. Save location

The video will be saved in the “output/video” folder

2. Video acceleration

If your comfyui does not have triton and sageattn installed, please delete
WanVideo Torch Compile Settings for WAN2.1 video generation
Change WanVideo Model Loader's attention_mode to sdpa
Otherwise, errors may occur

You can also join A Shuo’s membership group on WeChat: yumengashuo
The community provides:
1. Exclusive advanced comfyui workflows
2. Solutions to various complex problems
3. A Shuo's integration package to resolve environment conflicts, 100 original workflows
4. The latest international AI news
5. Community Q&A support