Seedance 1.5 Pro. The affordable Seedance, references included.
ByteDance's Seedance 1.5 Pro takes reference images, renders 4 to 12 second clips in seven formats with native audio, and costs less per second than Seedance 2.0 or 2.5. Pick it on any Video Generation node on the Treza canvas.
- 4 to 12 second clips
- 7 aspect ratios
- Native audio
- First and last frame control
- Reference images
- Up to 1080p
Seedance 1.5 Pro is the lower-cost member of the Seedance family, and its version number undersells it. It accepts reference images, so a product or character stays recognizable across separate generations, something Seedance 2.5 does not offer. It renders any exact length from 4 to 12 seconds, covers seven aspect ratios from 21:9 ultrawide to the extra-tall 9:21, and generates picture and sound together in a single pass.
On Treza it sits in the Video Generation node's model picker, a natural first stage in a pipeline: draft and do reference work on 1.5 Pro, then hand the winning prompt to Seedance 2.5 for a 30 second take or to Veo 3.1 for a hero render. Switch audio off while you explore and the rate halves. Prepaid credits, no subscription, and only successful runs are charged.
References at a lower rate
Wire in product photos or character art as references and the subject carries across separate generations, for less per second than Seedance 2.0 or 2.5.
Seven formats, 9:21 included
1:1, 3:4, 9:16, 9:21, 4:3, 16:9, and 21:9. One model covers square feeds, stories, the extra-tall frame, and ultrawide banners.
Keyframes or references, per shot
Pin a first and last frame for openers and reveals that land exactly. Set a frame and the node uses keyframes; leave frames empty and it uses your references.
Silent drafts at half the rate
Audio is generated in one pass with the picture, and switching it off halves the per-second rate. Iterate silent, then render the keeper with sound.
What to make with Seedance 1.5 Pro
Real prompts, and what comes back. Every one runs on a Video Generation node on the Treza canvas.
“This ceramic mug (photos attached) on a sunlit kitchen shelf, slow push-in”
A product shot where the mug matches your catalog photos.
“Same mug, steam rising, 9:16 for stories”
A vertical cut with the same product carried over.
“This illustrated fox mascot (reference attached) runs through autumn leaves”
Your character on model, ready for the next episode.
“A 9:21 frame of rain running down a neon sign at night”
An extra-tall clip, taller than a standard story frame.
“Four silent drafts of a coffee pour from different angles, 6 seconds each”
A low-cost batch to choose an angle from before adding sound.
“Start on this closed box, end on the open box with the product inside (both attached)”
A 12 second reveal pinned to both frames.
Seedance 1.5 Pro 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 1.5 Pro
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 1.5 Pro as an API, priced per clip
The Seedance 1.5 Pro API
Build a pipeline with Seedance 1.5 Pro 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 1.5 Pro pricing
Prepaid credits, no subscription. Each clip is charged at Seedance 1.5 Pro'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 1.5 Pro, answered
How does Seedance 1.5 Pro compare to Seedance 2.0 and 2.5?
It costs less per second than either. Like Seedance 2.0 it accepts reference images, which Seedance 2.5 does not. Clips run 4 to 12 seconds, against 15 on 2.0 and 30 on 2.5. Draft and do reference work on 1.5 Pro, and move to Seedance 2.5 when a single take has to run longer than 12 seconds.
Does turning off audio lower the cost?
Yes. Seedance 1.5 Pro's rate with audio is exactly double its rate without, so silent drafts cost half. The Generate audio switch sits on the node: leave it off while you explore and turn it on for the final render.
What reference images can I use with Seedance 1.5 Pro?
Subject and style references: product photos, packaging, illustrated characters and mascots, locations, and style frames. Seedance screens out photos of recognizable real people, so for a clip built from a portrait or a team photo, switch the node to Wan 2.7, which accepts them.
How much does Seedance 1.5 Pro cost on Treza?
Treza uses prepaid credits with no subscription. Each clip is charged at Seedance 1.5 Pro's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Seedance 1.5 Pro through an API?
Yes. Build a pipeline that uses Seedance 1.5 Pro 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.