SD 2 Text-to-Video VIP (Pro) by ByteDance. Generates high-quality cinematic video from a text prompt with priority routing, native audio-visual sync, up to 2K resolution, and 4–15 second duration.
About this model
SD 2 Text-to-Video VIP (Pro) generates high-quality cinematic videos directly from text prompts using priority routing for faster queue times. Featuring native audio-visual synchronization, up to 2K resolution, and support for 4–15 second durations, this VIP tier delivers the same top-quality output as the standard pro model with reduced wait times.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.30/sec (pro) | VIP priority routing with the same high-quality output as standard pro. |
| Fal.ai | Not available | SD 2 VIP priority tier not available. |
| Replicate | Not available | SD 2 VIP priority tier not available. |
VIP priority routing with the same high-quality output as standard pro.
SD 2 VIP priority tier not available.
SD 2 VIP priority tier not available.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text description of the video to generate. Use @character:<id> to anchor the video to a Seedance 2 character — automatically switches to image-to-video mode. Use @omni-character:<char_id> for a trained Kinovi character. | A cinematic shot of a futuristic city at night with neon lights reflecting on wet streets. |
| 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 |
Text description of the video to generate. Use @character:<id> to anchor the video to a Seedance 2 character — automatically switches to image-to-video mode. Use @omni-character:<char_id> for a trained Kinovi character.
A cinematic shot of a futuristic city at night with neon lights reflecting on wet streets.Output video aspect ratio.
16:9Video duration in seconds.
5Enable high bitrate mode for better visual fidelity. Produces larger files.
falseDeveloper documentation
Write your prompt: Describe your video scene in detail. Include motion cues ("camera panning right"), lighting ("golden hour"), style ("cinematic"), and subject details.
Set aspect ratio: Choose from 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9 depending on your target platform.
Choose duration: Set between 4 and 15 seconds. Longer durations increase cost proportionally.
Use character references: Include @character:<request_id> from a SD 2 Character generation to anchor the video to a specific character, or @omni-character:<char_id> for a trained character.
Submit and poll: The API returns a request_id. Poll /predictions/{request_id}/result or use a webhook URL for completion notification.
Frequently asked
VIP endpoints use priority routing which reduces queue wait times, making them ideal for time-sensitive workflows. Output quality and model capabilities are identical to the standard pro tier.
Yes. Use @character:<request_id> from a completed SD 2 Character generation to anchor the video to a character identity. The request automatically switches to image-to-video mode with the character sheet as the reference. You can also use @omni-character:<char_id> for trained omni characters.
Cost is charged per second of video generated. A 5-second video at the pro rate costs $1.25, while a 10-second video costs $2.50. The fast tier costs proportionally less.