Text to VideoImage to VideoReference to Video

Multi-Reference Video with Seedance 2 Mini

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.

What makes Seedance 2 Mini Reference-to-Video different

Up to 15 pieces of reference media

Feed the model up to 9 reference images, 3 reference videos (15 seconds combined), and 3 audio tracks in one generation. Images lock characters, products, and styles; videos transfer motion and pacing; audio can drive lip-sync and timing. That is full Seedance 2 multimodal referencing at the family's lowest price.

Character consistency you can afford to iterate on

Reference-driven generation usually takes several attempts to dial in. At about $0.06-$0.12 per second, Mini makes those attempts cheap: a 5-second 720p test costs about $0.61, so you can refine how the model uses your references without watching the budget drain — then keep the recipe.

Address references directly in the prompt

Your prompt names the media it should use — 'the woman from image 1 walks through the scene from image 2, moving like video 1'. That explicit addressing keeps multi-character scenes untangled and makes generations reproducible: swap image 1 for a new face and the rest of the shot holds.

A budget on-ramp to reference workflows

Mini is the tier to learn reference-to-video on. Once a reference set works, the same board can route it to standard Seedance 2 Reference to Video for 1080p output, or to Seedance 2.5, which extends the ceiling to 30 images, 10 videos, and 30-second durations — no re-uploading, since your references already live on the Scenetra canvas.

Playground

Seedance 2 Mini Reference-to-Video
playground

A timelapse of a flower blooming in a sunlit meadow, cinematic quality

Drop images or click to upload

5
720p
auto
true
Generate
Resultpreview
Sample output from Seedance 2 Mini Reference-to-Video

Try Seedance 2 Mini Reference-to-Video in Scenetra

Open Playground

Parameters

ParameterTypeDescriptionDefault
PrompttextReference your media in the prompt as 'image 1', 'video 1', 'audio 1', etc.
Reference Imagesimage uploadUp to 9 reference images for character consistency, style, and composition.
Reference Videosvideo uploadUp to 3 reference videos (≤15s total) for motion transfer and style.
Reference Audioaudio uploadUp to 3 audio files for audio-driven generation and lip-sync.
DurationselectLength of the generated video in seconds.4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 155
ResolutionselectOutput video resolution.480p · 720p720p
Aspect RatioselectVideo aspect ratio (defaults to matching the primary reference media).auto · 21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16auto
Generate AudioselectGenerate synchronized audio with the video.false · truetrue

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

Duration480p720p
5 seconds$0.29$0.61
10 seconds$0.57$1.22

Use cases

Characters & AI influencers

  • Consistent character series
  • Outfit and scene swaps
  • Multi-character skits
  • Persona tests at low cost

Brand & product

  • On-model product videos
  • Brand style transfer
  • Mascot animations
  • Campaign variant batches

Motion & choreography

  • Motion transfer from clips
  • Dance and action pacing
  • Camera-move mimicry
  • Music-driven timing tests

Audio-driven clips

  • Lip-sync from a voice track
  • Beat-matched edits
  • Narrated scene tests
  • Dialogue continuity checks

Related models

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.

Can I try it for free?+

Yes — Scenetra gives new accounts free welcome credits and a 7-day trial, and Mini's pricing makes them go far: a 5-second 720p reference generation is about $0.61. After that it is pay-per-generation from your credit balance, with no subscription gate.

How much does Seedance 2 Mini reference to video cost?+

The same rate as Mini's other modes: about $0.06 per second at 480p and $0.12 per second at 720p, regardless of how many references you attach. A 10-second 720p generation is about $1.22.

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.

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 Free