ByteDance · Video
Clips up to 30 seconds from text, frames or references — photo, video and audio.
Maker: ByteDance
10–66 
/ per second
30s · 480p/720p/1080p
text→video · photo→video · audioSeedance 2.5 by ByteDance generates 4–30 second videos at 480p, 720p, or 1080p. Three ways to set the scene: text only, first and last frames, or a set of references — up to 30 photos, 10 videos and 10 audio files. The model writes the soundtrack itself. Prompts run up to 30,000 characters.
| Type | Video generation (text-to-video, image-to-video, video-to-video) |
|---|---|
| Animate a photo | Yes |
| Input frames | up to 30 photos |
| References | up to 10 videos and 10 audio files |
| Audio | yes, native |
| Clip length | 30s |
| Resolution | 480p, 720p, 1080p |
| Prompt length | 30000 characters |
| Provider model | ByteDance Seedance 2.5 |
| Released | 2026-06-23 |
Clips up to 30 seconds from text, frames or references — photo, video and audio. It is a video model by ByteDance (ByteDance Seedance 2.5), available on Mixer AI pay-as-you-go — 10–66 coins per second.
Pay as you go, no plans — 10–66 coins per second. The exact price is shown before you run it.
Yes — upload a photo as a frame or reference and the model turns it into video. Text-to-video also works.
No. Mixer AI is pay-as-you-go: you top up a balance in coins and spend it only on the generations you want. Available on the site and in the Telegram bot @addbeer_bot.
Mixer AI
Open in Telegram
