SD 2 Omni Reference by ByteDance. Generate videos using up to 9 image references and up to 3 audio references. Reference images in your prompt with @image1, @image2, etc. and audio with @audio1, @audio2, etc.
About this model
Seedance 2 Omni Reference is a comprehensive multi-modal video generation tool that combines up to 9 image references and up to 3 audio references in a single generation. Reference images are labeled in your prompt as @image1, @image2, etc., and audio files as @audio1, @audio2, etc., giving you precise control over which elements anchor your video. Ideal for narrative-driven productions, music videos, branded content, and complex visual storytelling where multiple visual and sonic elements need to coexist in harmony.
Perfect for filmmakers, music video directors, commercial producers, and creators who need sophisticated multi-element coordination. At $1.25 per generation, muapi's unified API makes this advanced capability accessible without the complexity of traditional multi-track production workflows.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $1.25 per generation | Single transparent price covers complex multi-element video coordination. No subscription needed—pay only per video, making sophisticated reference-driven production accessible without expensive production software. |
Single transparent price covers complex multi-element video coordination. No subscription needed—pay only per video, making sophisticated reference-driven production accessible without expensive production software.
* 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
Seedance 2 Omni Reference costs $1.25 per generation on muapi. This single charge covers processing up to 9 image references and 3 audio references into one coordinated video generation.
Images are referenced as @image1, @image2, etc., in the order you list them in images_list. Audio files are referenced as @audio1, @audio2, etc., in the order they appear in audio_files. Your prompt directs how each element is used—e.g., '@image1 shows the hero product transitioning to @image2 lifestyle scene' with '@audio1 voiceover narrating throughout.'
Audio files should be in standard formats (MP3, WAV, AAC). Images can be JPEG, PNG, or WebP. All files must be accessible via public URL. Audio duration and image aspect ratios should be considered when planning your video composition.