Generate
Back to Models
Models/bytedance/video · text-to-video · image-to-video · reference-to-video · first-last-framePass-through

Seedance 2.0 Mini

Seedance 2.0 Mini is the leanest 2.0 tier for testing story beats, motion, framing, and sound without giving up the family's four core workflows. MachGen supports Text to Video, Image to Video, First & Last Frame, and Reference to Video at 480p or 720p, with Adaptive framing and Smart duration alongside fixed controls.

Current MachGen support
Text to VideoImage to VideoReference to VideoFrame to Frame4-15s480p / 720pPer type: 9 image / 3 video / 3 audio12 references combinedOptional audioSeed control
Starting at $0.033 / s
480p$0.033/s
720p$0.08/s
480p · with input video$0.02/s
720p · with input video$0.045/s
Live public pricebook · input-video rows bill input + output secondsSee full pricebook
Overview

Seedance 2.0 Mini

Seedance 2.0 Mini is the leanest 2.0 tier for testing story beats, motion, framing, and sound without giving up the family's four core workflows. MachGen supports Text to Video, Image to Video, First & Last Frame, and Reference to Video at 480p or 720p, with Adaptive framing and Smart duration alongside fixed controls.

Seedance 2.0 Mini examples for cost-efficient native-audio video, image animation, frame transitions, and multimodal references.

Model guide

Why choose Seedance 2.0 Mini

Key strengths

  • The most cost-efficient Seedance 2.0 tier for testing motion, visual continuity, and native sound quickly.
  • The same four core workflows span text, a start image, a first-and-last-frame pair, and mixed references.
  • Adaptive framing and Smart duration reduce setup when exploration matters more than a fixed delivery spec.
  • Reference generation accepts up to 9 image, 3 video, and 3 audio references within a 12-file combined limit.

Good fit for

  • Storyboard motion tests, social drafts, pitch concepts, and rapid A/B prompt studies.
  • Animating approved key art while preserving the subject and opening composition.
  • Testing physical transitions between two designed frames before a higher-cost final.
  • Reference-led experiments where several visual and audio ideas must work on one timeline.
Supported on MachGen

Inputs and output settings

This table reflects the model routes and controls currently exposed by MachGen.

ModeRequired inputAvailable settings
Text to VideoText promptResolution: 480p, 720p
Aspect ratio: Adaptive, 21:9, 16:9, 9:16, 1:1, 4:3, 3:4
Duration: 4-15s, Smart
Frame rate: 24fps
Optional generated audio
Seed control
Image to VideoText prompt and source image; optional end frameResolution: 480p, 720p
Aspect ratio: Adaptive, 21:9, 16:9, 9:16, 1:1, 4:3, 3:4
Duration: 4-15s, Smart
Frame rate: 24fps
Optional generated audio
Seed control
Reference to VideoPer-type limits: up to 9 images, up to 3 videos, up to 3 audio files; 12 references combined, plus a text promptResolution: 480p, 720p
Aspect ratio: Adaptive, 21:9, 16:9, 9:16, 1:1, 4:3, 3:4
Duration: 4-15s, Smart
Frame rate: 24fps
Optional generated audio
Seed control
First & Last FrameText prompt, start frame, and end frameResolution: 480p, 720p
Aspect ratio: Adaptive, 21:9, 16:9, 9:16, 1:1, 4:3, 3:4
Duration: 4-15s, Smart
Frame rate: 24fps
Optional generated audio
Seed control
Workflow

Using Seedance 2.0 Mini

  1. Choose a supported generation mode in Playground.
  2. Add the required prompt and source or reference assets.
  3. Select output settings from the controls shown for that mode.
  4. Generate, then inspect the returned asset before reusing the settings through the API.

Practical guidance

  • Describe the subject, action or composition, environment, and visual direction in a clear order.
  • For image animation, describe the intended motion and camera behavior instead of repeating what is already visible.
  • Give each reference a clear role in the prompt, using the names inserted by the Playground.
  • Use compatible start and end frames, then describe the transition between them.
  • When audio is enabled, include any dialogue, ambience, or sound cues that matter to the scene.
Best results

How to get better Seedance 2.0 Mini results

  • Keep each short clip focused on one readable action and one primary camera move.
  • For image animation, describe what changes after frame one instead of repeating what the image already shows.
  • Use compatible first and last frames and describe the physical path between them, including what must stay unchanged.
  • Start with the minimum useful reference set; add an asset only when it contributes information the prompt cannot state clearly.
Limits

Limits and availability

  • MachGen admits only the modes and settings listed above for this catalog model.
  • Source assets must finish uploading before a request can be submitted.
  • Generated results can vary between requests, including when the same prompt and settings are reused.
  • Seedance 2.0 Mini is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.
Learn more

Learn more

For model background, technical details, and architecture, see the Seedance 2.0 Mini API reference.

Try this model in the MachGen Playground.

Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.

Pricing

Seedance 2.0 Mini pricing

See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.

On MachGen

Seedance 2.0 Mini on MachGen

Deployment: Pass-through. Seedance 2.0 Mini is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

The Playground and API sections on this page list the inputs and output settings exposed for this model.