Skip to content

Seedance 2.5: director-level AI video from four inputs

Build consistent 30-second videos from text, images, audio, and source clips. Seedance 2.5 gives teams stronger creative control across every shot.

Text + image inputAudio referencesVideo references
Start generatingView pricing
Reference-guided
Prompt
Image
Audio
Video

Multimodal control without the slow post pipeline

Use reference media to lock in motion, mood, sound direction, and shot continuity, then ship campaign-ready concepts faster.

Why Seedance 2.5 on Sceneform

Up to 50 references and 30 seconds of continuous motion, inside a workspace built for fast campaign production.

How to create with Seedance 2.5

Start with intent, add references, then turn rough creative direction into a tighter finished sequence.

Motion prompt

A couple in eveningwear on a misty road at night, slow dolly in, cinematic

Dolly inNightCinematic
01

Write the story beat

Describe the subject, motion, camera intention, and overall mood.

02

Layer references

Add images, audio, or source footage to steer composition and pacing.

10s1080p30fps
03

Set the output

Choose the format and workflow that fits your social or launch asset.

Final cut
04

Iterate to final

Refine with new references and prompt edits until the clip is ready.

Built for controllable AI video production

Reference-driven control, stable motion, and cinematic output from one workflow.

Unified multimodal input

Combine text prompts with image, audio, and video references in one flow.

Director-level control

Guide performance, camera movement, lighting, and visual tone with references.

Campaign-ready output

Generate premium short-form clips for ads, launch films, and social.

What teams build with Seedance 2.5

Use one model for controlled concepting, reference-heavy revisions, and polished social delivery.

Turn brand references and music cues into finished ad concepts without a long post handoff.

50 refsAcross image, video, and audio
3.3xFaster campaign iteration

Simple pricing that scales with you.

Pick the plan for how much you post. Every model on every plan. Unused credits roll over. Cancel anytime.

Choose a Sceneform plan

Creator

$19/month

Billed monthly

For solo creators posting every week

500 credits every month

  • Up to 250 AI images
  • Up to 50 AI videos
  • Up to 1.5 hours of AI voiceover
  • Roll over up to 1,000 credits

Pro, selected

Most popular
$49/month

Billed monthly

For creators posting daily across channels

1,300 credits every month

  • Up to 650 AI images
  • Up to 130 AI videos
  • Up to 4 hours of AI voiceover
  • Roll over up to 2,600 credits

Studio

$99/month

Billed monthly

For brands and production teams

2,700 credits every month

  • Up to 1,350 AI images
  • Up to 270 AI videos
  • Up to 9 hours of AI voiceover
  • Roll over up to 5,400 credits

Scale

$199/month

Billed monthly

For agencies running always-on content

5,500 credits every month

  • Up to 2,750 AI images
  • Up to 550 AI videos
  • Up to 18 hours of AI voiceover
  • Roll over up to 11,000 credits
Every plan includesEvery model, 90+ and countingReusable AI personasSceneform Studio editorCommercial usage rights

Credit use varies by model and settings. Exact credits are shown before every generation.

Your selection

Pro plan

1,300 credits added monthly

$49/month

$49 due now ยท billed monthly

We'll use this for your receipt and secure sign-in link.

Secure Stripe checkout ยท Cancel anytime ยท 3-day refund policy ยท Terms

Need more than Scale?

Custom volume and invoicing for businesses and agencies.

Contact us

Frequently asked questions about Seedance 2.5

Seedance 2.5 is ByteDanceโ€™s multimodal video generation model for creating continuous clips from text, image, audio, and video direction.
Start with text, a first frame, or a first and last frame. You can also direct the result with up to 30 images, 10 videos, and 10 audio clips, with 50 references in total.
Choose Seedance 2.5 when your brief needs consistent characters, locations, sound, and visual style across a clip up to 30 seconds long.
Yes. It is designed for ad, launch, and social workflows where teams need more control over characters, products, sets, pacing, and sound.
Yes. Add up to 10 audio references to guide rhythm, sound cues, or pacing. Audio references must be paired with at least one image or video reference.

Start creating with Seedance 2.5

Direct a continuous 30-second video with text, image, audio, and video references.

Start creating