SD 2 First & Last Frame VIP (Pro) by ByteDance. Generate video that transitions between two reference images with priority routing. Provide 1 image for start-frame-only, or 2 images for both start and end frames.
About this model
SD 2 First & Last Frame VIP (Pro) generates video that transitions between two reference images with priority routing. Provide one image as the opening frame, or two images for a complete start-to-end transition. Uses the pro model for maximum output quality at 2K resolution.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.30/sec (pro) | VIP priority routing with pro-quality output. |
| Fal.ai | Not available | Not available. |
| Replicate | Not available | Not available. |
VIP priority routing with pro-quality output.
Not available.
Not available.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text description guiding the transition between frames. | Two people having a street interview, the interviewer holds a microphone. |
| Frame Images | array | 1 image = first frame only; 2 images = first and last frame. Use 'adaptive' aspect ratio to match the reference image geometry. | https://d3adwkbyhxyrtq.cloudfront.net/ai-images/186/712345784292/4a8c5c70-abcc-4920-873e-b0e219986453.jpg |
| Aspect Ratio | Enum (7 options) | Output video aspect ratio. 'adaptive' matches the reference image (recommended); concrete ratios may crop or pad. | adaptive |
| 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 guiding the transition between frames.
Two people having a street interview, the interviewer holds a microphone.1 image = first frame only; 2 images = first and last frame. Use 'adaptive' aspect ratio to match the reference image geometry.
https://d3adwkbyhxyrtq.cloudfront.net/ai-images/186/712345784292/4a8c5c70-abcc-4920-873e-b0e219986453.jpgOutput video aspect ratio. 'adaptive' matches the reference image (recommended); concrete ratios may crop or pad.
adaptiveVideo duration in seconds.
5Enable high bitrate mode for better visual fidelity. Produces larger files.
falseDeveloper documentation
Upload 1 or 2 images: A single image is used as the first frame only. Two images define both the opening and closing frames of the video.
Write a prompt: Describe the transition. Example: "A smooth transformation from dawn to dusk over a mountain range."
Set duration: Choose 4–15 seconds. The aspect ratio is determined automatically from the input images.
Retrieve results: Use the request_id to poll or provide a webhook_url for notification.
Frequently asked
First & Last Frame uses keyframe mode — both images become structural anchors for the video. Image-to-Video with 2 images works the same way in VIP mode. The key difference is conceptual: First & Last Frame is designed for controlled start-to-end transitions.
You can use @character:<request_id> or @omni-character:<char_id> in the prompt to include character identity guidance, though these modes work best with actual frame images.