Image models
Seedream 4.5
Seedream 4.5 — fast, high-fidelity AI image generation & editing.
| modelId | seedream-4-5-edit, seedream-4-5-text-to-image |
| Modality | image |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Edit | seedream-4-5-edit | POST /api/v1/generate | prompt, image_urls, aspect_ratio, quality |
| Text To Image | seedream-4-5-text-to-image | POST /api/v1/generate | prompt, aspect_ratio, quality |
| Poll task | — | GET /api/v1/task/{id}?model=seedream-4-5-edit | — |
Edit — seedream-4-5-edit
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | A text description of the image you want to generate Max 3000 characters. (default: Relight this interior into a cozy loft at golden hour, warm sun raking across exposed brick, dust motes drifting in the air and a soft amber glow pooling on the wooden floor.) |
| image_urls | string[] | Yes | Upload an image file to use as input for the API (image URL) |
| aspect_ratio | string | Yes | Width-height ratio of the image, determining its visual form. (options: 1:1 | 4:3 | 3:4 | 16:9 | 9:16 | 2:3 | 3:2 | 21:9) (default: 1:1) |
| quality | string | Yes | Basic outputs 2K images, while High outputs 4K images. (options: basic | high) (default: basic) |
| nsfw_checker | boolean | No | A configurable parameter. Defaults to true in the Playground. (true/false) (default: true) |
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"seedream-4-5-edit","input":{"prompt":"A photorealistic portrait of a red fox in a snowy forest, soft morning light, shallow depth of field, 85mm.","image_urls":["https://example.com/input.jpg"],"aspect_ratio":"1:1","quality":"basic","nsfw_checker":true}}'Text To Image — seedream-4-5-text-to-image
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | A text description of the image you want to generate Max 3000 characters. (default: A lone cellist on a candlelit stage, bow paused mid-note, a warm spotlight haloing her shoulders as rows of empty velvet seats dissolve into darkness, cinematic still with shallow depth of field.) |
| aspect_ratio | string | Yes | Width-height ratio of the image, determining its visual form. (options: 1:1 | 4:3 | 3:4 | 16:9 | 9:16 | 2:3 | 3:2 | 21:9) (default: 1:1) |
| quality | string | Yes | Basic outputs 2K images, while High outputs 4K images. (options: basic | high) (default: basic) |
| nsfw_checker | boolean | No | A configurable parameter. Defaults to true in the Playground. (true/false) (default: true) |
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"seedream-4-5-text-to-image","input":{"prompt":"A photorealistic portrait of a red fox in a snowy forest, soft morning light, shallow depth of field, 85mm.","aspect_ratio":"1:1","quality":"basic","nsfw_checker":true}}'