Seedance 2.0 Fast. Seedance 2.0 with sound, for less per second.
ByteDance's lower-cost tier of Seedance 2.0. Four to fifteen second clips with native audio, from a prompt, first and last frames, or reference images, in seven aspect ratios.
- 4 to 15 second clips
- 7 aspect ratios
- Native audio
- First and last frame control
- Reference images
- 480p or 720p
Seedance 2.0 Fast is a tier of ByteDance's Seedance 2.0 video model, billed at a lower rate per second of output than the full model. It takes the same kinds of input: a text prompt, an exact first frame, a first and last frame to land between, or reference images to carry a product or character into a new scene. Clips run from 4 to 15 seconds at 480p or 720p, with sound generated alongside the picture.
On Treza it sits in the Video Generation node's picker and in chat. Pick 480p for the cheapest drafts, wire reference images into the node to keep a subject consistent, and chain the clip into captions, narration, and publishing like any other step. It bills from prepaid credits, and only successful runs are charged.
Native audio
Ambient sound and effects come back with the picture, so a clip plays as a finished beat without a separate sound pass.
First and last frames
Open on an exact image, or give it both ends of the shot and let the model fill the motion in between.
Reference images
Wire reference images into the node to keep a product or a character recognizable in a scene it was never photographed in.
Seven aspect ratios
From 21:9 widescreen to 9:21 tall, including 9:16 for Shorts and Reels and 1:1 for feeds, at any whole second from 4 to 15.
What to make with Seedance 2.0 Fast
Real prompts, and what comes back. Every one runs in Treza chat or as a node on the canvas.
“A barista pours steamed milk into a latte in a sunlit cafe, slow push-in, 9:16”
A vertical cafe beat with the pour audible.
“Start on this product photo (attached): morning light drifts across it as the camera eases in”
Image-to-video from your exact opening frame.
“Use these photos of our backpack as references: it hangs on a hook in a mountain hut, rain on the window”
The same product carried into a new scene.
“Go from the first frame (attached) to the last frame (attached) in 6 seconds”
A shot that lands exactly where you planned.
“Ten 4 second hook variations for an ad test, 480p”
Low-cost drafts to pick a winner from.
“A 15 second drift over a night market, sizzling grills and chatter, 21:9”
A long ultrawide shot with its own sound.
Seedance 2.0 Fast is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with Seedance 2.0 Fast
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
Seedance 2.0 Fast as an API, priced per clip
The Seedance 2.0 Fast API
Build a pipeline with Seedance 2.0 Fast on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
Seedance 2.0 Fast pricing
Prepaid credits, no subscription. Each clip is charged at Seedance 2.0 Fast's own rate from your balance, shown before you run, and only successful generations are charged, so a failed run costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
Seedance 2.0 Fast, answered
How is Seedance 2.0 Fast different from Seedance 2.0?
It takes the same inputs, first and last frames and reference images included, and bills a lower rate per second of output. It renders at 480p or 720p, where the full Seedance 2.0 also offers 1080p and 4K. Run one prompt through both on two nodes and let the output decide.
Does Seedance 2.0 Fast generate audio?
Yes. Clips come back with sound generated alongside the picture. For narration over the footage, add a Text to Speech node and mix it in with the Sequence node.
Can it use photos of real people as references?
ByteDance screens reference images and rejects recognisable real people before a job starts. For photos of people, try Wan 2.7 or Grok Imagine instead.
How much does Seedance 2.0 Fast cost on Treza?
Treza uses prepaid credits with no subscription. Each clip is charged at Seedance 2.0 Fast's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Seedance 2.0 Fast through an API?
Yes. Build a pipeline that uses Seedance 2.0 Fast and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.