> ## Documentation Index
> Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Create Seedream images
> Use CometAPI POST /v1/images/generations for Seedream text-to-image and image-to-image generation — supports sequential multi-image output and reference images.
## Overview
Generate images using ByteDance's Seedream models through the standard OpenAI-compatible `/v1/images/generations` endpoint. Supports both **text-to-image** and **image-to-image** generation.
For the full model list, see the [Models page](/overview/models). For detailed parameter documentation from the provider, see the [VolcEngine documentation](https://www.volcengine.com/docs/6791/1541523).
When using sequential (multi-image) generation, set `sequential_image_generation` to `auto` and optionally configure `sequential_image_generation_options.max_images` to limit the number of output images. The total number of reference images plus generated images must be **≤ 15**.
## Image-to-image
Pass one or more reference images via the `image` parameter (array of URLs or base64 data URIs) along with a text prompt. Supports up to 14 reference images.
## Returned URL gives AccessDenied?
The returned `url` is a signed object-storage link that **contains `&` and other special characters**.\
If you copy the raw JSON and paste it directly into a browser or script, shell escaping or terminal truncation may strip the signature parameters, resulting in:
```json theme={null}
\{"Code":"AccessDenied","Message":"Access Denied","EC":"0003-00000015"\}
```
**How to fix:**
* **curl**: pipe through `| jq -r '.data[].url'` to extract the URL cleanly.
* **Python**: use `result.data[0].url` or `image["url"]` — the string is already complete; pass it directly to `requests.get()` or `webbrowser.open()`.
* **JavaScript**: same idea — `result.data[0].url`.
* **General**: make sure `&` and `%` in the URL are not truncated or double-escaped.
## OpenAPI
````yaml api/openapi/image/seededit-seedream/post-bytedance-image-generation.openapi.json POST /v1/images/generations
openapi: 3.1.0
info:
title: bytedance-image-generation(seedream) API
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/v1/images/generations:
post:
summary: bytedance-image-generation(seedream)
operationId: bytedance_image_generation
requestBody:
required: true
content:
application/json:
schema:
type: object
description: >-
Parameters for Seedream image generation (text-to-image and
image-to-image).
required:
- model
- prompt
properties:
model:
type: string
description: >-
Model to use. See the [Models page](/overview/models) for
current Seedream model IDs.
default: doubao-seedream-5-0-260128
prompt:
type: string
description: >-
Text prompt describing the image to generate. Supports both
Chinese and English. Recommended max 300 Chinese characters
or 1000 English characters.
default: a cat wearing a scarf sitting by the window
response_format:
type: string
description: >-
Output format. `url` returns a temporary image link (valid
for 24 hours); `b64_json` returns base64-encoded image data.
default: url
enum:
- url
- b64_json
size:
type: string
description: >-
Output resolution. Presets `2K`, `4K`, or exact pixels like
`2048x2048`, `2304x1728`, `2848x1600`, `1600x2848`, etc.
Default: `2048x2048`.
default: 2048x2048
image:
type: array
items:
type: string
description: >-
Reference image(s) for image-to-image generation. Each item
is a public URL or base64 data URI
(`data:image/png;base64,...`). Supports up to 14 reference
images. Supported formats: jpeg, png, webp, bmp, tiff, gif.
watermark:
type: boolean
description: >-
When `true`, adds an 'AI Generated' watermark to the
bottom-right corner of the output image.
default: true
guidance_scale:
type: number
description: >-
Controls how closely the output follows the prompt. Higher
values increase adherence but may reduce naturalness. Range:
1.0–10.0. Not supported by Seedream 5.0 (ignored).
default: 2.5
seed:
type: integer
description: >-
Random seed for reproducible outputs. Range: -1 to
2147483647. Use -1 (default) for random generation. Legacy
parameter — ignored by newer models.
default: -1
sequential_image_generation:
type: string
description: >-
Controls sequential (multi-image) generation mode.
- `auto`: model decides whether to generate a sequence based
on the prompt
- `disabled`: always generate a single image
default: disabled
enum:
- auto
- disabled
sequential_image_generation_options:
type: object
description: >-
Configuration for sequential (multi-image) generation. Only
effective when `sequential_image_generation` is `auto`.
properties:
max_images:
type: integer
description: >-
Maximum number of images to generate in this request.
Range: [1, 15]. Total reference images + generated
images must be ≤ 15.
default: 15
output_format:
type: string
description: 'Output image file format. Options: `png`, `jpeg`.'
default: jpeg
enum:
- png
- jpeg
default:
model: doubao-seedream-5-0-260128
prompt: a cat wearing a scarf sitting by the window
response_format: url
size: 2K
watermark: false
examples:
Seedream 5.0 — Text to Image:
summary: Seedream 5.0 — Text to Image
value:
model: doubao-seedream-5-0-260128
prompt: >-
a cat wearing a scarf sitting by the window watching rain,
illustration style
size: 2K
response_format: url
watermark: false
Seedream 5.0 — Image to Image:
summary: Seedream 5.0 — Image to Image (single ref)
value:
model: doubao-seedream-5-0-260128
prompt: transform into watercolor painting style, vibrant colors
image:
- https://example.com/photo.jpg
size: 2K
response_format: url
watermark: false
Seedream 5.0 — Sequential (Multi-Image):
summary: Seedream 5.0 — Sequential multi-image generation
value:
model: doubao-seedream-5-0-260128
prompt: >-
a 4-panel comic strip of a cat's daily routine: waking up,
eating breakfast, playing, and sleeping
size: 2K
response_format: url
sequential_image_generation: auto
sequential_image_generation_options:
max_images: 4
watermark: false
Seedream 4.5 — Text to Image:
summary: Seedream 4.5 — Text to Image
value:
model: doubao-seedream-4-5-251128
prompt: a futuristic cityscape at sunset with flying cars
size: 2K
response_format: url
watermark: false
Seedream 4.0 — Text to Image:
summary: Seedream 4.0 — Text to Image
value:
model: doubao-seedream-4-0-250828
prompt: an oil painting of a mountain lake at dawn
size: 2K
response_format: url
watermark: false
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: object
required:
- created
- data
- usage
properties:
model:
type: string
description: The model used for generation.
created:
type: integer
description: Unix timestamp (seconds) when the image was generated.
data:
type: array
description: Array of generated image objects.
items:
type: object
properties:
url:
type: string
description: >-
Signed download URL for the generated image (valid
for 24 hours). Returned when `response_format` is
`url`.
b64_json:
type: string
description: >-
Base64-encoded image data. Returned when
`response_format` is `b64_json`.
size:
type: string
description: >-
Pixel dimensions of the generated image, e.g.
`2048x2048`. Returned by some models.
usage:
type: object
description: Resource usage information for this request.
properties:
generated_images:
type: integer
description: Number of images successfully generated.
output_tokens:
type: integer
description: >-
Tokens consumed by the generated image(s). Calculated
as sum(width × height) / 256.
total_tokens:
type: integer
description: >-
Total tokens consumed (currently equals
output_tokens).
x-codeSamples:
- lang: Shell
label: Text to Image (5.0)
source: |
curl -s https://api.cometapi.com/v1/images/generations \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedream-5-0-260128",
"prompt": "a cat wearing a scarf sitting by the window watching rain, illustration style",
"size": "2K",
"response_format": "url",
"watermark": false
}' | jq -r '.data[].url'
- lang: Shell
label: Image to Image (5.0)
source: |
curl -s https://api.cometapi.com/v1/images/generations \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedream-5-0-260128",
"prompt": "transform into watercolor painting style, vibrant colors",
"image": ["https://example.com/photo.jpg"],
"size": "2K",
"response_format": "url",
"watermark": false
}' | jq -r '.data[].url'
- lang: Shell
label: Text to Image (4.5)
source: |
curl -s https://api.cometapi.com/v1/images/generations \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedream-4-5-251128",
"prompt": "a futuristic cityscape at sunset with flying cars",
"size": "2K",
"response_format": "url",
"watermark": false
}' | jq -r '.data[].url'
- lang: Python
label: Text to Image (5.0)
source: |
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key=os.environ["COMETAPI_KEY"],
)
result = client.images.generate(
model="doubao-seedream-5-0-260128",
prompt="a cat wearing a scarf sitting by the window watching rain, illustration style",
size="2K",
response_format="url",
extra_body={"watermark": False},
)
for i, image in enumerate(result.data, 1):
print(f"image_{i}: {image.url}")
- lang: Python
label: Image to Image (5.0)
source: |
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key=os.environ["COMETAPI_KEY"],
)
result = client.images.generate(
model="doubao-seedream-5-0-260128",
prompt="transform into watercolor painting style, vibrant colors",
size="2K",
response_format="url",
extra_body={
"image": ["https://example.com/photo.jpg"],
"watermark": False,
},
)
for i, image in enumerate(result.data, 1):
print(f"image_{i}: {image.url}")
- lang: Python
label: Text to Image (4.5)
source: |
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key=os.environ["COMETAPI_KEY"],
)
result = client.images.generate(
model="doubao-seedream-4-5-251128",
prompt="a futuristic cityscape at sunset with flying cars",
size="2K",
response_format="url",
extra_body={"watermark": False},
)
for i, image in enumerate(result.data, 1):
print(f"image_{i}: {image.url}")
- lang: JavaScript
label: Text to Image (5.0)
source: |
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.cometapi.com/v1",
apiKey: process.env.COMETAPI_KEY,
});
const result = await client.images.generate({
model: "doubao-seedream-5-0-260128",
prompt:
"a cat wearing a scarf sitting by the window watching rain, illustration style",
size: "2K",
response_format: "url",
extra_body: { watermark: false },
});
result.data.forEach((image, i) => {
console.log(`image_${i + 1}: ${image.url}`);
});
- lang: JavaScript
label: Image to Image (5.0)
source: |
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.cometapi.com/v1",
apiKey: process.env.COMETAPI_KEY,
});
const result = await client.images.generate({
model: "doubao-seedream-5-0-260128",
prompt: "transform into watercolor painting style, vibrant colors",
size: "2K",
response_format: "url",
extra_body: {
image: ["https://example.com/photo.jpg"],
watermark: false,
},
});
result.data.forEach((image, i) => {
console.log(`image_${i + 1}: ${image.url}`);
});
- lang: JavaScript
label: Text to Image (4.5)
source: |
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.cometapi.com/v1",
apiKey: process.env.COMETAPI_KEY,
});
const result = await client.images.generate({
model: "doubao-seedream-4-5-251128",
prompt: "a futuristic cityscape at sunset with flying cars",
size: "2K",
response_format: "url",
extra_body: { watermark: false },
});
result.data.forEach((image, i) => {
console.log(`image_${i + 1}: ${image.url}`);
});
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication. Use your CometAPI key.
````