SD 2 Omni Reference VIP Fast by ByteDance. Faster video generation using up to 9 image references, up to 3 video clips, and up to 3 audio references with priority routing. Reference materials in your prompt with @image1…@image9, @video1…@video3, and @audio1…@audio3.
About this model
SD 2 Omni Reference VIP Fast generates reference-guided videos using the faster model variant with priority routing. Supports up to 9 image references, up to 3 audio references, and character identity references via @character and @omni-character syntax — at a lower cost per second than the pro VIP tier.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.21/sec | VIP fast tier — most cost-efficient option for reference-guided video with priority routing. |
| Fal.ai | Not available | Not available. |
| Replicate | Not available | Not available. |
VIP fast tier — most cost-efficient option for reference-guided video with priority routing.
Not available.
Not available.
** 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, @video1…@video3 for videos, and @audio1…@audio3 for audio. Use @character:<request_id> for a Seedance 2 character sheet or @omni-character:<char_id> for a trained Kinovi character. Multiple characters are supported. | @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 |
| Video Reference URLs | array | Up to 3 reference video clip URLs (MP4, max 15s each). Each Nth video corresponds to @videoN in the prompt. | undefined |
| 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 (6 options) | Output video aspect ratio. | 16:9 |
| Duration (seconds) | int | Video duration in seconds. | 5 |
| High Bitrate | boolean | Enable high bitrate mode for better visual fidelity. Produces larger files. | false |
Video description. Use @image1…@image9 to reference images, @video1…@video3 for videos, and @audio1…@audio3 for audio. Use @character:<request_id> for a Seedance 2 character sheet or @omni-character:<char_id> for a trained Kinovi character. Multiple characters are supported.
@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 video clip URLs (MP4, max 15s each). Each Nth video corresponds to @videoN in the prompt.
undefinedUp 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.
5Enable high bitrate mode for better visual fidelity. Produces larger files.
falseDeveloper documentation
Upload references: Add up to 9 images in images_list and up to 3 audio files in audio_files.
Write your prompt: Reference materials with @image1–@image9, @audio1–@audio3, @character:<id>, or @omni-character:<char_id>.
Set aspect ratio and duration: Choose from standard ratios and 4–15 second durations.
Submit: Returns a request_id for polling or webhook delivery.
Frequently asked
Yes. All reference types are supported: @image1–@image9, @audio1–@audio3, @character:<request_id>, and @omni-character:<char_id>. The only difference is generation speed and cost.
Use the fast variant for high-volume workflows, prototyping, or cost-sensitive production. Use the pro variant when maximum output quality is required.