Pricing

Seedance 2.0 is ByteDance's latest multi-modal AI video generation model. It accepts images, videos, audio, and text as inputs—up to 12 files per generation. Using an @ reference system, you can direct every aspect of your video: motion, camera work, character appearance, visual style, and audio rhythm.

Seedance 2.0's @ reference system lets you control video generation like a director. Upload a dance video for motion reference, an image for character appearance, and audio for rhythm—then combine them in a single prompt. No other model offers this level of multi-modal control.

Inputs: up to 9 images, 3 videos (total ≤15s), 3 audio files, and text prompts—12 files max per generation. Outputs: 4-15 second videos in 1080p with 6 aspect ratios (16:9, 9:16, 4:3, 3:4, 21:9, 1:1) and native audio generation.

Seedance 2.0 renders HD video in 2-5 seconds—a major speed improvement over previous versions. Complex multi-reference generations may take slightly longer but rarely exceed 10 seconds.

Yes! All videos generated on Clpo are watermark-free and licensed for commercial use including social media, advertising, websites, and professional presentations. You own full rights to your creations.