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.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runbytedance/seedream/5.0/pro/editInput Schema
4 parameters · 1 required · 3 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | The text prompt used to edit the image. |
images | string[] | Optional | List of URLs of input reference images. Up to 10 images are supported; if more are sent, only the last 10 are used. |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16 |
output_format | string | Optional | The file format of the generated image. · Options: jpeg, png · Default: "jpeg" jpegpng |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "bytedance/seedream/5.0/pro/edit",
"images": [
"https://static.sandbase.ai/examples/bytedance/seedream/5.0/pro/edit/input_images_0.png",
"https://static.sandbase.ai/examples/bytedance/seedream/5.0/pro/edit/input_images_1.png",
"https://static.sandbase.ai/examples/bytedance/seedream/5.0/pro/edit/input_images_2.png"
],
"prompt": "Replace the product in Figure 1 with that in Figure 2. Seamlessly render the logo in Figure 3 into the product design, in a frosted glass texture.",
"output_format": "jpeg"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"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 ratio | Price 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 case | Why this model fits |
|---|---|
| Product and campaign compositing | Merge product, logo, texture, and scene references while keeping perspective and lighting consistent. |
| Local retouching and object changes | Describe an addition, removal, recolor, material swap, or cleanup in a specific area. |
| Posters and information graphics | Create or revise dense layouts where hierarchy, typography, and visual organization matter. |
| Multilingual localization | Translate or replace copy while preserving the surrounding design and visual balance. |
| Portrait and lifestyle refinement | Improve 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
| Property | Details |
|---|---|
| Model ID | bytedance/seedream/5.0/pro/edit |
| Required input | prompt |
| Reference images | Optional array; up to 10 images are used, and when more are supplied only the last 10 are retained |
| Aspect ratios | 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 |
| Output formats | jpeg (default) or png |
| Output | Downloadable image URL with optional content type |
| Execution | Asynchronous |
Related Models
bytedance/seedream/5.0/pro— create new Seedream 5.0 Pro images directly from a prompt.bytedance/seedream/4.5/edit— compare with the previous Seedream editing generation.bytedance/seedream/4.0— use an earlier Seedream route for general image creation.

