SandBase is live — $1 in free credits on signupStart free ›

Bytedance modelsimage generation api

bytedance/seedvr/upscale/video

Seedvr Upscale Video by Bytedance - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.

Input
The input video to be processed
The format of the output video. Allowed values: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif).
The random seed used for the generation process.
The quality of the output video. Allowed values: low, medium, high, maximum.
01
The noise scale to use for the generation process. Range: 0 to 1.
The target resolution to upscale to when `upscale_mode` is `target`. Allowed values: 720p, 1080p, 1440p, 2160p.
110
Upscaling factor to be used. Will multiply the dimensions with this factor when `upscale_mode` is `factor`. Range: 1 to 10.
The write mode of the output video. Allowed values: fast, balanced, small.
The mode to use for the upscale. If 'target', the upscale factor will be calculated based on the target resolution. If 'factor', the upscale factor will be used directly. Allowed values: target, factor.
Idle

Example output — click Run to generate your own

API README

SeedVR2 Video Upscaler

SeedVR2 Video Upscaler restores and enlarges an existing video while maintaining continuity across its frames. It is designed for footage whose content and timing are already established but whose delivered resolution needs improvement. The output remains a video asset, making the route a post-processing step rather than a new scene generator.

The workflow can target a named resolution or apply a scale factor, then encode the result in one of several delivery formats. Quality and write-mode controls provide a practical balance between visual fidelity, processing profile, and file size. This makes the route adaptable to review copies, web delivery, and higher-resolution masters without changing the underlying sequence.

Highlights

  • Temporal consistency during upscaling. The exact video route explicitly emphasizes coherent restoration across frames. This addresses the stability requirement that distinguishes video enhancement from independent still-image processing.
  • One-step video restoration. SeedVR2 is described as a one-step large diffusion-transformer model for video restoration. It restores the sequence without relying on an additional diffusion prior.
  • Flexible-resolution restoration design. The SeedVR2 project states that the model can restore videos at any resolution. The route turns that capability into target-resolution and scale-factor workflows.
  • High-resolution adaptive attention. The published architecture uses adaptive window attention for high-resolution restoration. This supports the model's focus on processing visually demanding video frames within a unified restoration system.

Pricing

Billing unitPrice
Base price per request$0.001

When to Use

✅ Good fit❌ Consider alternatives
Enlarging existing footage while preserving frame continuityGenerating a new video from a written scene
Preparing a lower-resolution clip for HD, 2K, or 4K deliveryProcessing only one still image
Creating a scaled version when a fixed target tier is unnecessaryRequiring motion retiming, new shots, or timeline editing
Selecting an output codec for a downstream media pipelineNeeding the original compressed bitstream unchanged
Balancing output quality against file-writing prioritiesRequiring a custom delivery codec outside the listed formats

Prompt Guide

This is an input-guided video restoration route and does not use a descriptive text prompt. Supply an accessible video, choose either a target-resolution workflow or a scale-factor workflow, then set the output encoding options.

Video: <publicly accessible video URL>
Upscale mode: <target or factor>
Target resolution or factor: <matching value>
Output format: <X264 mp4, VP9 webm, PRORES4444 mov, or GIF>
Quality/write mode: <desired processing profile>

Example request:

{
  "video": "https://example.com/input-video.mp4",
  "upscale_mode": "target",
  "target_resolution": "1080p",
  "output_format": "X264 (.mp4)",
  "output_quality": "high",
  "output_write_mode": "balanced"
}

Technical Specs

SpecValue
Model IDbytedance/seedvr/upscale/video
Video inputvideo URL field
Upscale modetarget or factor; default factor
Target resolution720p, 1080p, 1440p, or 2160p; default 1080p
Upscale factor1 to 10; default 2
Noise scale0 to 1; default 0.1
Output formatsX264 (.mp4), VP9 (.webm), PRORES4444 (.mov), or GIF
Output qualitylow, medium, high, or maximum
Write modefast, balanced, or small
OutputVideo URL and content type
ExecutionAsynchronous job

Related

Related Models

bytedance/seedvr/upscale/imageSeedvr Upscale Image by Bytedance - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.bytedance/seedvr/upscale/image/seamlessSeedvr Upscale Image is Bytedance's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.bytedance/seedream/4.0Seedream 4.0 by Bytedance - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.bytedance/seedream/4.0/editSeedream 4.0 Edit is Bytedance's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.bytedance/seedream/4.5A new-generation image creation model from ByteDance, Seedream 4.5 integrates text-to-image generation and image editing into a single unified architecture, delivering high-fidelity visuals, precise prompt control, and seamless creative workflows for professional AIGC applications.bytedance/seedream/4.5/editA new-generation image creation model from ByteDance, Seedream 4.5 integrates text-to-image generation and image editing into a single unified architecture, delivering high-fidelity visuals, precise prompt control, and seamless creative workflows for professional AIGC applications.bytedance/seedream/5.0/liteSeedream 5.0 Lite — Fast Text-to-Image API The lightweight version of Seedream 5.0, delivering high-quality, low-latency AI image generation from text prompts. Ideal for real-time creative tools, e-commerce visuals, and high-volume AIGC pipelines.bytedance/seedream/5.0/lite/editSeedream 5.0 Lite — Fast Text-to-Image API The lightweight version of Seedream 5.0, delivering high-quality, low-latency AI image generation from text prompts. Ideal for real-time creative tools, e-commerce visuals, and high-volume AIGC pipelines.