Fast, Affordable Cinematic Video with Seedance 2 Mini

Seedance 2.0 Mini is the fast, lower-cost tier of ByteDance's Seedance 2 video model. It generates cinematic clips of 4 to 15 seconds from text prompts, with synchronized audio — dialogue, sound effects, and music — on by default. On Scenetra it comes in three modes: Text to Video, Image to Video, and Reference to Video, each available as a node in the visual workflow editor.

The model itself is paid per second of video, but you can try it without paying: new Scenetra accounts get free welcome credits and a 7-day trial, which comfortably covers first generations at Mini's low prices. After that you pay per generation from your credit balance — no subscription gates the model and there is nothing to cancel.

On Scenetra, Seedance 2 Mini costs about $0.06 per second at 480p and $0.12 per second at 720p, audio included. A 5-second 720p clip is about $0.61 and a 10-second one about $1.22 — roughly half the per-second rate of standard Seedance 2.

It depends on the job. Mini costs roughly half as much per second and is built for speed, but it tops out at 720p, while standard Seedance 2 offers a 1080p super-resolution tier. A common workflow is to iterate on Mini until the prompt and timing are right, then re-run the final take on standard Seedance 2 — on Scenetra both are nodes on the same board, so switching is one connection.

Scenetra runs in the browser, so there is nothing to install and no API key to manage. Sign up, drop a Seedance 2 Mini node onto your board, type a prompt (put spoken dialogue in double quotes), pick duration and resolution, and generate. The result lands on the board where you can wire it into upscalers, sequencers, or other models.

Any whole-second duration from 4 to 15 seconds in a single generation — the same range as standard Seedance 2. If you need longer single-pass clips, Seedance 2.5 goes up to 30 seconds at a higher per-second price.

Yes — audio is on by default. The model generates synchronized voice, sound effects, and background music together with the picture, so dialogue is lip-synced without post-processing. You can toggle audio off if you want silent footage.

For social feeds, ads tests, and anything delivered at 720p or below, yes — it is the same Seedance 2 generation with native audio, just without the 1080p tier. For large-screen or broadcast delivery you will want standard Seedance 2 or another 1080p-capable model; on Scenetra you can run the same prompt through several models side by side and judge for yourself.