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

Bytedance modelsimage generation api

bytedance/seedream/5.0/pro/edit

Seedream 5.0 Pro is Bytedance's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Input
The text prompt used to edit the image.

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

List of URLs of input reference images. Up to 10 images are supported; if more are sent, only the last 10 are used.
The file format of the generated image. Allowed values: jpeg, png.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
Idle

Example output — click Run to generate your own

API README

Seedream 5.0 Pro Image Editing

Seedream 5.0 Pro Edit is a professional image-editing route for turning natural-language direction and up to ten visual references into a finished image. It is designed for production work where the edit must understand not only what should change, but also where the change belongs and how it should blend with the existing composition.

The model combines spatial and regional understanding with stronger image–text alignment, structural coherence, typography, and photographic realism. That makes it useful for precise local revisions, multi-image composition, dense marketing graphics, multilingual creative, and polished assets that need to preserve layout, perspective, lighting, and material continuity.

Highlights

  • Spatially precise editing. Understands positions and regional semantics so prompts can target specific objects or areas while leaving the rest of the composition coherent.
  • Multi-image creative fusion. Uses as many as ten reference images to combine products, subjects, logos, styles, or materials inside one directed edit.
  • Production-quality realism. Reconstructs physical lighting, shadows, surfaces, and skin texture for edits that remain visually integrated rather than looking pasted on.
  • Design and multilingual strength. Handles text-rich layouts and more than ten widely used languages, making it suitable for posters, infographics, campaign assets, and localized creative.

Pricing

The current public request schema exposes ten aspect-ratio presets. Every supported preset is billed at the model card's base price of $0.0675 per request.

Output aspect ratioPrice per request
21:9$0.0675
16:9$0.0675
3:2$0.0675
4:3$0.0675
5:4$0.0675
1:1$0.0675
4:5$0.0675
3:4$0.0675
2:3$0.0675
9:16$0.0675

When to Use

Use caseWhy this model fits
Product and campaign compositingMerge product, logo, texture, and scene references while keeping perspective and lighting consistent.
Local retouching and object changesDescribe an addition, removal, recolor, material swap, or cleanup in a specific area.
Posters and information graphicsCreate or revise dense layouts where hierarchy, typography, and visual organization matter.
Multilingual localizationTranslate or replace copy while preserving the surrounding design and visual balance.
Portrait and lifestyle refinementImprove styling, setting, lighting, or skin detail without losing a natural photographic finish.

Prompt Guide

Identify each reference by its role, then state the exact change, protected elements, target placement, and desired finish. For multi-image work, use explicit phrases such as “use image 1 as the base,” “take the product from image 2,” and “apply the logo from image 3.” Add constraints for composition, typography, perspective, lighting, material, and realism instead of relying on a short style label.

{
  "prompt": "Use image 1 as the base scene. Replace its bottle with the product from image 2, preserving the bottle's proportions and label. Apply the logo from image 3 as a subtle frosted-glass embossing on the front. Match the original camera angle, contact shadow, warm studio lighting, and reflections; keep the background and headline unchanged.",
  "images": [
    "https://example.com/base-scene.png",
    "https://example.com/product.png",
    "https://example.com/logo.png"
  ],
  "aspect_ratio": "4:5",
  "output_format": "png"
}

Technical Specs

PropertyDetails
Model IDbytedance/seedream/5.0/pro/edit
Required inputprompt
Reference imagesOptional array; up to 10 images are used, and when more are supplied only the last 10 are retained
Aspect ratios21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
Output formatsjpeg (default) or png
OutputDownloadable image URL with optional content type
ExecutionAsynchronous

Related Models

Related Models

bytedance/seedream/5.0/proSeedream 5.0 Pro 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/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.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/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/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/seed/v2/miniSeed V2 Mini by Bytedance - advanced AI model for llm. Delivers high-quality results with fast inference, suitable for both creative and production workflows.