Seedance 2 Mini Reference to Video
Seedance 2 Mini Reference-to-Video generates consistent videos from up to 9 reference images, 3 reference videos, and 3 audio tracks. Reference subjects directly in your prompt as 'image 1', 'video 1', etc. for character consistency and motion transfer — at ByteDance's fast, affordable Mini pricing.
84% less than the priciest provider (5 compared). Same model, same output.
Up to 9 reference images for character, style or scene. Cite in the prompt as @Image1 and so on.
Up to 3 reference videos (mp4/mov), total duration up to 15s. Reference video seconds are billed as input.
Up to 3 reference audio files (wav/mp3). Requires at least one reference image or video.
Duration
Duration of the video in seconds (4-15). Billed per second.
Resolution
Video resolution. Higher resolutions cost more per second.
Aspect Ratio
Aspect ratio of the generated video. 'adaptive' follows the prompt or the primary media.
Audio
Synchronized audio: voice, sound effects and music generated in the same pass. Some sellers cannot switch audio off, so turning it off can change the winning price.
Content
What the video contains. Sellers differ in what they allow: 'general' (no faces) can unlock lower prices; 'mature' routes only to sellers without content restrictions.
84% less than the priciest provider (5 compared). Same model, same output.
Your result renders here.
Use Seedance 2 Mini Reference to Video via the API
Generate with Seedance 2 Mini Reference to Video from your own code. Async by design: submit a generation, get a run id back instantly, poll until it completes. Billed in credits at the best available provider price — from $0.06 per second.
1 — Start a generation
curl -X POST https://app.scenetra.com/api/v1/generate/seedance-2-mini-ref2v \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"@Image1 walks through a sunlit market holding @Image2, handheld follow shot, crowd murmur","reference_images":["https://example.com/person.jpg","https://example.com/product.jpg"],"duration":"5"}'Response (202)
{
"runId": "run_abc123",
"status": "PENDING",
"model": "seedance-2-mini-ref2v",
"estimatedCredits": 122,
"statusUrl": "/api/v1/runs/run_abc123"
}2 — Poll until COMPLETED (every 2-5 seconds)
curl https://app.scenetra.com/api/v1/runs/run_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Response
{
"runId": "run_abc123",
"status": "COMPLETED",
"progress": { "completed": 1, "total": 1 },
"outputs": [
{ "type": "video", "url": "https://images.scenetra.com/..." }
],
"error": null,
"estimatedCredits": 122
}Request fields
| Field | Type | Description | Default |
|---|---|---|---|
| prompt* | string | Cite reference inputs in order with @-syntax: @Image1, @Video1, @Audio1. | — |
| reference_images | string[] (https URLs) | Up to 9 reference images for character, style or scene. Cite in the prompt as @Image1 and so on. | — |
| reference_videos | string[] (https URLs) | Up to 3 reference videos (mp4/mov), total duration up to 15s. Reference video seconds are billed as input. | — |
| reference_audios | string[] (https URLs) | Up to 3 reference audio files (wav/mp3). Requires at least one reference image or video. | — |
| duration | string | Duration of the video in seconds (4-15). Billed per second.4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 5 |
| resolution | string | Video resolution. Higher resolutions cost more per second.480p · 720p · 1080p · 4k | 720p |
| aspect_ratio | string | Aspect ratio of the generated video. 'adaptive' follows the prompt or the primary media.adaptive · 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 | adaptive |
| generate_audio | string | Synchronized audio: voice, sound effects and music generated in the same pass. Some sellers cannot switch audio off, so turning it off can change the winning price.false · true | true |
| subject_content | string | What the video contains. Sellers differ in what they allow: 'general' (no faces) can unlock lower prices; 'mature' routes only to sellers without content restrictions.general · people · mature | people |
| callbackUrl | string (https URL) | Optional. When the run finishes (completed or failed), we POST the final run status to this URL — same shape as the poll response, plus model, params, and chargedCredits. Best-effort; polling remains the source of truth. | |
Unknown fields are rejected with a helpful 400. Media fields take https URLs. There is no provider parameter — every run is routed to the cheapest capable provider automatically.
Good to know
Billing
Runs bill your account credits at provider cost with 0% markup. The submit response includes the credit estimate; failed generations are refunded automatically. Add ?dryRun=1 to get the estimate without running anything.
Errors
Errors are always { "error": { "code", "message" } } with stable codes: unauthorized, model_not_available, invalid_parameter, insufficient_credits, rate_limited. A failed run is not an HTTP error — poll responses report status: "FAILED" with the reason.
What makes Seedance 2 Mini Reference to Video different
The cheapest way to run Seedance
Mini is the lowest-priced tier in the Seedance 2 family: about $0.06 per second at 480p and $0.12 at 720p — roughly half the per-second rate of standard Seedance 2. A 5-second 720p clip costs about $0.61, so you can afford to generate five takes of a shot and keep the best one instead of betting everything on a single expensive render.
Real Seedance 2 audio, not a stripped-down version
Mini keeps the family's signature feature: synchronized audio generated together with the picture — dialogue, sound effects, and background music, on by default. Put spoken lines in double quotes inside your prompt and characters deliver them lip-synced. Toggle audio off with one switch when you want silent footage.
4 to 15 seconds, six aspect ratios plus auto
Pick any whole-second duration from 4 to 15 and any ratio from 21:9 cinematic widescreen to 9:16 vertical — or leave the ratio on auto and let the model infer it from your prompt. Resolutions are 480p for quick drafts and 720p for delivery; there is no 1080p tier on Mini, which is part of how it stays cheap.
Draft on Mini, finish on the big models
On a Scenetra board, Mini earns its keep as an iteration engine: explore prompts and timing at Mini prices, then wire the winning prompt into a standard Seedance 2 node for 1080p, or a Seedance 2.5 node for 30-second durations — all side by side on the same canvas, no copy-pasting between apps.
More made with Seedance 2 Mini Reference to Video
Parameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt* | text | Text prompt describing the video. Use double quotes for spoken dialogue. | — |
| Duration | select | Length of the generated video in seconds.4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 5 |
| Resolution | select | Output video resolution.480p · 720p | 720p |
| Aspect Ratio | select | Video aspect ratio (or 'auto' to let the model choose).auto · 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 | auto |
| Generate Audio | select | Generate synchronized audio with dialogue, SFX, and background music.false · true | true |
Pricing
From $0.06 per second
Pay per generation — only pay for what you use.
480p
$0.06/s
per second
720p
$0.12/s
per second
What a video costs
| Duration | 480p | 720p |
|---|---|---|
| 5 seconds | $0.29 | $0.61 |
| 10 seconds | $0.57 | $1.22 |
Use cases
Social content
- High-volume short clips
- Vertical 9:16 stories
- Sound-on hooks
- Daily posting pipelines
Iteration & previz
- Cheap prompt exploration
- Shot timing tests
- Animatics and previz
- A/B testing concepts
Marketing & ads
- Ad variant batches
- UGC-style spots
- Concept testing before finals
- Localized versions at scale
Education & explainers
- Illustrative b-roll
- Scene visualizations
- Short dialogue skits
- Course intro clips
Frequently asked questions
What is Seedance 2 Mini Reference to Video?+
It is the reference-driven mode of ByteDance's Seedance 2 Mini: instead of (or alongside) a text prompt, you supply up to 9 reference images, 3 reference videos, and 3 audio tracks, and the model generates a new 4-15 second video that keeps your characters, styles, motion, or audio timing consistent. On Scenetra it runs as a node in the visual workflow editor.
How many reference images and videos can I use?+
Up to 9 reference images, up to 3 reference videos totaling 15 seconds or less, and up to 3 audio files — all in a single generation. Refer to them in the prompt as 'image 1', 'video 2', 'audio 1' and so on, so the model knows which reference plays which role.
How is Mini's reference mode different from Seedance 2.5 Reference to Video?+
Capacity and price. Mini accepts up to 9 images, 3 videos, and 3 audio tracks, with durations of 4-15 seconds at up to 720p. Seedance 2.5 raises that to 30 images, 10 videos, and 10 audio tracks with durations up to 30 seconds — at roughly two and a half times Mini's per-second rate. Prototype on Mini, scale up on 2.5 when the shot demands it.
Can audio drive the video?+
Yes — attach up to 3 audio files and reference them in the prompt, and the model can use a voice track for lip-sync or a music track for pacing. The generated video also ships with its own synchronized audio by default, which you can toggle off.
Related models
Seedance 2
ByteDance's Seedance 2.0 generates cinematic videos from text prompts with synchronized audio — voice, sound effects, and background music. Pick any duration from 4 to 15 seconds and resolutions up to 1080p, with per-second pricing that keeps 480p drafting cheap.
View model →Seedance 2.5
ByteDance's Seedance 2.5 generates cinematic videos up to 30 seconds from text prompts with synchronized audio — voice, sound effects, and background music — built in by default. The newest Seedance generation, with mp4 or high-fidelity mov output for multi-round editing pipelines.
View model →Start creating with Seedance 2 Mini Reference to Video
Use Seedance 2 Mini Reference to Video alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started