AI Text to Video Generator
Describe your vision and let AI create stunning videos
Balanced speed and quality, but face ID consistency is weaker than 800.
Each scene lasts 5s. Current video duration: 5s.
Use AI to generate prompts (experimental)
Please sign in to use text to video feature
Frequently Asked Questions
Common questions about the Text to Video feature
How should I write a good prompt?
Be specific and descriptive. Include details about the scene, characters, actions, camera movements, lighting, and style. For example: 'A majestic dragon flying over snow-capped mountains at sunset, camera slowly zooms out revealing a medieval castle below, cinematic lighting, 4k quality'.
Which resolution should I choose?
384 is mainly for GIFs or simple animations; its real video quality is limited. 512 is a balanced choice, but in i2v face consistency is not always guaranteed. 768 provides the best face consistency.
What video sizes are supported?
We support three aspect ratios: 16:9 (512x288) for landscape videos, 4:3 (448x336) for classic format, and 1:1 (384x384) for square videos suitable for social media.
There are so many img2vid products on the market. What makes your img2vid different?
Our img2vid generates a 20-second video in about 2 minutes at 512 resolution, with an estimated cost of $0.04, while maintaining stable quality.