Superb effect! Superb effect! Superb effect!

Important things are said three times!!!

Simply upload an image, and the built-in large language model will automatically generate suitable text-to-video prompts based on your image.

Optimized and re-optimized based on the prompts from Wanxiang wan2.1.

Completely solves the trouble of not knowing how to write prompts. By the way, frame interpolation is added, and the quality is improved to pseudo-720p.