SD 2 Omni Reference (Fast) by ByteDance. Quickly generate videos using up to 9 image references and up to 3 audio references at reduced cost. Reference images in your prompt with @image1, @image2, etc. and audio with @audio1, @audio2, etc.
About this model
Seedance 2 Omni Reference (Fast) delivers the same multi-modal reference capability as the standard Omni Reference model—combining up to 9 image references and 3 audio files—but at reduced cost and faster processing speed. Use it for rapid iteration, client approvals, and production pipelines where speed matters more than maximum visual polish. Reference images are labeled @image1, @image2, etc., and audio as @audio1, @audio2, etc., in your prompt.
Ideal for high-volume content creators, advertising agencies, and production teams that need quick turnarounds on reference-heavy videos. At just $0.75 per generation, this fast variant makes multi-element video production cost-effective for iterative workflows and tight deadlines.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.75 per generation | Cost-effective fast-turnaround pricing for multi-element reference videos. At $0.75 per generation with no subscription, you can afford multiple iterations and drafts during production workflows. |
Cost-effective fast-turnaround pricing for multi-element reference videos. At $0.75 per generation with no subscription, you can afford multiple iterations and drafts during production workflows.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Video description. Use @image1…@image9 to reference images and @audio1…@audio3 for audio. To use a character sheet, reference it with @character:<request_id> (from a completed Seedance 2 Character generation). To use a trained Omni Reference character, reference it with @omni-character:<character_id> where character_id is the value returned by Omni Reference Train Character (e.g. char_1775422630065_4vbana). Both methods can be combined in the same prompt. Multiple characters are supported. Example: '@omni-character:char_1775422630065_4vbana walking through a neon-lit city at night'. | @image1 is the main character. The person walks along a city street at sunset, cinematic lighting. |
| Image URLs | array | Up to 9 reference image URLs (JPEG/PNG/WebP). Each Nth image corresponds to @imageN in the prompt. | https://d3adwkbyhxyrtq.cloudfront.net/ai-images/186/712345784292/4a8c5c70-abcc-4920-873e-b0e219986453.jpg |
| Audio Reference URLs | array | Up to 3 reference audio files (MP3/WAV, total max 15s). Each Nth audio corresponds to @audioN in the prompt. | undefined |
| Aspect Ratio | Enum (4 options) | Output video aspect ratio. | 16:9 |
| Duration (seconds) | int | Video duration in seconds (4–15). | 5 |
Video description. Use @image1…@image9 to reference images and @audio1…@audio3 for audio. To use a character sheet, reference it with @character:<request_id> (from a completed Seedance 2 Character generation). To use a trained Omni Reference character, reference it with @omni-character:<character_id> where character_id is the value returned by Omni Reference Train Character (e.g. char_1775422630065_4vbana). Both methods can be combined in the same prompt. Multiple characters are supported. Example: '@omni-character:char_1775422630065_4vbana walking through a neon-lit city at night'.
@image1 is the main character. The person walks along a city street at sunset, cinematic lighting.Up to 9 reference image URLs (JPEG/PNG/WebP). Each Nth image corresponds to @imageN in the prompt.
https://d3adwkbyhxyrtq.cloudfront.net/ai-images/186/712345784292/4a8c5c70-abcc-4920-873e-b0e219986453.jpgUp to 3 reference audio files (MP3/WAV, total max 15s). Each Nth audio corresponds to @audioN in the prompt.
undefinedOutput video aspect ratio.
16:9Video duration in seconds (4–15).
5Developer documentation
Frequently asked
The Fast variant generates videos at reduced cost ($0.75 vs. $1.25) with quicker processing, making it ideal for drafts and rapid iteration. Both accept up to 9 images and 3 audio files. Standard Omni Reference may offer slightly higher visual polish; use Fast when speed and cost matter most.
Seedance 2 Omni Reference (Fast) costs $0.75 per generation compared to $1.25 for the standard version—a 40% cost reduction. This makes it ideal for high-volume production and client approval workflows where multiple iterations are necessary.
Yes, the Fast variant supports the same up to 9 image references and 3 audio references. You reference them in your prompt using @image1, @image2, etc. and @audio1, @audio2, etc., exactly as in the standard Omni Reference model.