> ## 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.
# Crear imágenes de Seedream
> Usa la ruta POST /v1/images/generations de CometAPI para la generación de imágenes con Seedream con prompts de texto, imágenes de referencia, salida secuencial de imágenes y tareas async.
Usa la ruta compatible con OpenAI `POST /v1/images/generations` de CometAPI para ejecutar la generación de imágenes con Seedream. Este endpoint admite prompts de texto a imagen, solicitudes con imágenes de referencia y salida secuencial acotada de imágenes cuando el modelo seleccionado admite esos controles.
Esta página cubre `seedream-5-0-pro-260628` para solicitudes Pro de texto a imagen y `seedream-5-0-260128` para ejemplos de imágenes de referencia, secuenciales y async de Seedream 5.0. Para consultar la disponibilidad en tu cuenta, consulta la [página de modelos](/es/overview/models) o realiza una consulta a `/v1/models`. Para obtener detalles sobre los parámetros del proveedor, consulta la [API de generación de imágenes](https://docs.byteplus.com/en/docs/ModelArk/1541523) de BytePlus y el [tutorial de Seedream 4.0-5.0](https://docs.byteplus.com/en/docs/ModelArk/1824121).
## Elige una forma de solicitud
* Texto a imagen: envía `model`, `prompt`, `size` y controles de salida opcionales como `response_format`, `output_format` y `watermark`.
* Imagen a imagen: agrega `image` como un arreglo de URL HTTPS públicas o URI de datos. Usa un arreglo incluso cuando envíes una sola imagen de referencia.
* Prompt secuencial: establece `sequential_image_generation` en `auto` y usa `sequential_image_generation_options.max_images` como límite superior. El modelo puede devolver menos imágenes que el máximo.
* Tarea async: agrega `async: true` cuando quieras que la solicitud de creación devuelva `data.task_id` en lugar de mantener abierta la conexión HTTP.
Las imágenes de referencia más las imágenes generadas deben mantenerse dentro del límite del proveedor. Mantén acotadas las solicitudes secuenciales con `max_images`.
## Ejecuta una tarea de imagen async
Establece `async` en `true` para trabajos de imagen que tu cliente deba enviar y consultar. La solicitud de creación devuelve `data.task_id`; usa ese valor con [Recuperar una tarea de imagen de Seedream](/api/image/seededit-seedream/bytedance-image-generation-task) hasta que `data.status` sea `success` o `failure`.
Usa `2K` en los ejemplos async para solicitudes de Seedream 5.0. La compatibilidad de tamaños varía según el model ID, así que elige un tamaño compatible con el modelo antes de enviar una tarea async.
## Envía imágenes de referencia
Usa `data:image/png;base64,YOUR_BASE64_IMAGE` para datos de imagen en línea, o usa una URL HTTPS pública que el proveedor pueda recuperar. Los ejemplos de la referencia de la API muestran la forma JSON completa para cada tipo de solicitud.
## Lee las URL de salida
La `url` devuelta es un enlace firmado de almacenamiento de objetos y puede contener `&`, `%` y otros caracteres especiales. Extrae la URL del JSON ya analizado en lugar de copiar una línea parcial de la terminal. En los ejemplos de shell, `jq -r '.data[]?.url'` conserva la URL firmada completa.
## OpenAPI
````yaml api/openapi/image/seededit-seedream/post-bytedance-image-generation.openapi.json POST /v1/images/generations
openapi: 3.1.0
info:
title: Seedream image generation API
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/v1/images/generations:
post:
summary: Create Seedream images
operationId: bytedance_image_generation
requestBody:
required: true
content:
application/json:
schema:
type: object
description: >-
Parameters for Seedream image generation. Send JSON for
text-to-image, image-to-image, and sequential prompt requests.
required:
- model
- prompt
properties:
model:
type: string
description: >-
Seedream model ID to use. Query `/v1/models` or open the
[Models page](/overview/models) for available model IDs.
default: seedream-5-0-pro-260628
prompt:
type: string
description: >-
Text prompt describing the image or edit goal. Use a
concrete visual request, such as `a blue ceramic mug on a
white table, soft studio lighting`.
default: >-
A clean product-style render of a blue ceramic mug on a
white table, soft studio lighting.
response_format:
type: string
description: >-
Response image format. Use `url` for a temporary signed
image URL, or `b64_json` when you need base64 image data in
the response.
default: url
enum:
- url
- b64_json
size:
type: string
description: >-
Output resolution. Use a model-supported tier such as `2K`
or a model-supported `WIDTHxHEIGHT` value such as
`2048x2048`. Not every model ID accepts every tier.
default: 2K
image:
type: array
items:
type: string
description: >-
Optional reference images for image-to-image generation.
Each item can be a public HTTPS URL or a data URI such as
`data:image/png;base64,YOUR_BASE64_IMAGE`. Use an array even
for one image. Reference images plus generated images must
not exceed the provider limit.
watermark:
type: boolean
description: >-
When `true`, requests a visible AI-generated watermark on
the output image. Set `false` when your workflow handles
disclosure separately.
default: false
async:
type: boolean
description: >-
CometAPI asynchronous task mode. Set this to `true` to
return immediately with `data.task_id`, then poll the
Seedream image task endpoint `GET
/v1/images/generations/{task_id}` for the final image data.
default: false
output_format:
type: string
description: >-
Output image file format. Use `png` when you need lossless
output, or `jpeg` for smaller files.
default: png
enum:
- png
- jpeg
guidance_scale:
type: number
description: >-
Optional prompt-adherence control for model versions that
support it. Higher values can follow the prompt more closely
but may reduce naturalness. Omit this field when you do not
need model-specific tuning.
minimum: 1
maximum: 10
seed:
type: integer
description: >-
Optional random seed for reproducible attempts on model
versions that support seeding. Use `-1` or omit the field
for a random seed.
minimum: -1
maximum: 2147483647
default: -1
sequential_image_generation:
type: string
description: >-
Controls sequential prompt handling. Use `auto` to let the
model return a sequence when the prompt calls for one. Use
`disabled` for ordinary single-image requests.
default: disabled
enum:
- auto
- disabled
sequential_image_generation_options:
type: object
description: >-
Options for sequential prompt handling. This object is only
used when `sequential_image_generation` is `auto`.
properties:
max_images:
type: integer
description: >-
Maximum number of generated images allowed for the
request. This is an upper bound, not a guarantee that
the model returns that many images.
minimum: 1
maximum: 15
default: 2
default:
model: seedream-5-0-pro-260628
prompt: >-
A clean product-style render of a blue ceramic mug on a white
table, soft studio lighting.
size: 2K
response_format: url
output_format: png
watermark: false
examples:
Text to image (Pro):
summary: Text to image with a Pro Seedream model
value:
model: seedream-5-0-pro-260628
prompt: >-
A clean product-style render of a blue ceramic mug on a
white table, soft studio lighting.
size: 2K
response_format: url
output_format: png
watermark: false
Image to image (5.0):
summary: Use a reference image with Seedream 5.0
value:
model: seedream-5-0-260128
prompt: >-
Transform this product photo into a soft watercolor
illustration while preserving the main object layout.
image:
- data:image/png;base64,YOUR_BASE64_IMAGE
size: 2K
response_format: url
watermark: false
Sequential prompt (5.0):
summary: >-
Allow a sequence when the prompt calls for multiple related
images
value:
model: seedream-5-0-260128
prompt: >-
Create a two-step visual sequence showing a sprout growing
into a small plant, consistent flat illustration style.
size: 2K
response_format: url
sequential_image_generation: auto
sequential_image_generation_options:
max_images: 2
watermark: false
Async image task (5.0):
summary: Submit an async Seedream image task and poll by task ID
value:
model: seedream-5-0-260128
prompt: >-
A small blue origami bird on a white background, clean
product illustration.
size: 2K
response_format: url
async: true
watermark: false
responses:
'200':
description: >-
Image generation response. Synchronous requests return completed
image data. Async requests return a task response with
`data.task_id`.
content:
application/json:
schema:
oneOf:
- type: object
required:
- created
- data
properties:
created:
type: integer
description: >-
Unix timestamp in seconds when the image response was
created.
data:
type: array
description: >-
Generated image results. The array can contain one or
more images depending on the request and model
response.
items:
type: object
properties:
url:
type: string
description: >-
Temporary signed URL for the generated image.
Save or download the image before the URL
expires.
b64_json:
type: string
description: >-
Base64-encoded image data when `response_format`
is `b64_json`.
size:
type: string
description: >-
Pixel dimensions of the generated image when
returned by the model, such as `2048x2048`.
usage:
type: object
description: >-
Usage information for the request. Fields vary by
model and route.
properties:
input_images:
type: integer
description: >-
Number of reference images received by the route,
when reported.
generated_images:
type: integer
description: Number of generated images, when reported.
output_tokens:
type: integer
description: >-
Image output tokens charged for the generated
image data, when reported.
total_tokens:
type: integer
description: Total tokens reported for the request.
- type: object
title: Async task response
required:
- code
- data
properties:
code:
type: string
description: >-
Request status code. A successful async submit returns
`success`.
example: success
message:
type: string
description: Optional status message.
data:
type: object
required:
- task_id
- status
- data
properties:
task_id:
type: string
description: >-
Task ID to pass to `GET
/v1/images/generations/{task_id}`.
status:
type: string
description: Task state for the submitted image generation job.
enum:
- pending
- success
- failure
data:
type: array
description: >-
Empty at submit time. Poll the task endpoint to
receive final image data.
items:
type: object
example:
code: success
message: ''
data:
task_id:
status: pending
data: []
examples:
completed:
summary: Completed image response
value:
created: 1781075000
data:
- url: https:///.png
size: 2048x2048
usage:
generated_images: 1
total_tokens: 0
async_task:
summary: Async task response
value:
code: success
message: ''
data:
task_id:
status: pending
data: []
x-codeSamples:
- lang: Shell
label: Text to image (Pro)
source: |
curl -s https://api.cometapi.com/v1/images/generations \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5-0-pro-260628",
"prompt": "A clean product-style render of a blue ceramic mug on a white table, soft studio lighting.",
"size": "2K",
"response_format": "url",
"output_format": "png",
"watermark": false
}' | jq -r '.data[]? | .url // .b64_json'
- lang: Python
label: Text to image (Pro)
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/v1/images/generations",
headers={
"Authorization": "Bearer " + os.environ["COMETAPI_KEY"],
"Content-Type": "application/json",
},
json={"model": "seedream-5-0-pro-260628", "prompt": "A clean product-style render of a blue ceramic mug on a white table, soft studio lighting.", "size": "2K", "response_format": "url", "output_format": "png", "watermark": False},
timeout=180,
)
response.raise_for_status()
result = response.json()
for image in result.get("data", []):
print(image.get("url") or image.get("b64_json"))
- lang: JavaScript
label: Text to image (Pro)
source: >
const response = await
fetch("https://api.cometapi.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "seedream-5-0-pro-260628",
"prompt": "A clean product-style render of a blue ceramic mug on a white table, soft studio lighting.",
"size": "2K",
"response_format": "url",
"output_format": "png",
"watermark": false
}),
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
for (const image of result.data ?? []) {
console.log(image.url ?? image.b64_json);
}
- 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": "seedream-5-0-260128",
"prompt": "Transform this product photo into a soft watercolor illustration while preserving the main object layout.",
"image": [
"data:image/png;base64,YOUR_BASE64_IMAGE"
],
"size": "2K",
"response_format": "url",
"watermark": false
}' | jq -r '.data[]? | .url // .b64_json'
- lang: Python
label: Image to image (5.0)
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/v1/images/generations",
headers={
"Authorization": "Bearer " + os.environ["COMETAPI_KEY"],
"Content-Type": "application/json",
},
json={"model": "seedream-5-0-260128", "prompt": "Transform this product photo into a soft watercolor illustration while preserving the main object layout.", "image": ["data:image/png;base64,YOUR_BASE64_IMAGE"], "size": "2K", "response_format": "url", "watermark": False},
timeout=180,
)
response.raise_for_status()
result = response.json()
for image in result.get("data", []):
print(image.get("url") or image.get("b64_json"))
- lang: JavaScript
label: Image to image (5.0)
source: >
const response = await
fetch("https://api.cometapi.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "seedream-5-0-260128",
"prompt": "Transform this product photo into a soft watercolor illustration while preserving the main object layout.",
"image": [
"data:image/png;base64,YOUR_BASE64_IMAGE"
],
"size": "2K",
"response_format": "url",
"watermark": false
}),
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
for (const image of result.data ?? []) {
console.log(image.url ?? image.b64_json);
}
- lang: Shell
label: Sequential prompt (5.0)
source: |
curl -s https://api.cometapi.com/v1/images/generations \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5-0-260128",
"prompt": "Create a two-step visual sequence showing a sprout growing into a small plant, consistent flat illustration style.",
"size": "2K",
"response_format": "url",
"sequential_image_generation": "auto",
"sequential_image_generation_options": {
"max_images": 2
},
"watermark": false
}' | jq -r '.data[]? | .url // .b64_json'
- lang: Python
label: Sequential prompt (5.0)
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/v1/images/generations",
headers={
"Authorization": "Bearer " + os.environ["COMETAPI_KEY"],
"Content-Type": "application/json",
},
json={"model": "seedream-5-0-260128", "prompt": "Create a two-step visual sequence showing a sprout growing into a small plant, consistent flat illustration style.", "size": "2K", "response_format": "url", "sequential_image_generation": "auto", "sequential_image_generation_options": {"max_images": 2}, "watermark": False},
timeout=180,
)
response.raise_for_status()
result = response.json()
for image in result.get("data", []):
print(image.get("url") or image.get("b64_json"))
- lang: JavaScript
label: Sequential prompt (5.0)
source: >
const response = await
fetch("https://api.cometapi.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "seedream-5-0-260128",
"prompt": "Create a two-step visual sequence showing a sprout growing into a small plant, consistent flat illustration style.",
"size": "2K",
"response_format": "url",
"sequential_image_generation": "auto",
"sequential_image_generation_options": {
"max_images": 2
},
"watermark": false
}),
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
for (const image of result.data ?? []) {
console.log(image.url ?? image.b64_json);
}
- lang: Shell
label: Async image task (5.0)
source: |
RESPONSE=$(curl -s https://api.cometapi.com/v1/images/generations \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5-0-260128",
"prompt": "A small blue origami bird on a white background, clean product illustration.",
"size": "2K",
"response_format": "url",
"async": true,
"watermark": false
}')
printf "%s\n" "$RESPONSE" | jq -r '.data.task_id'
- lang: Python
label: Async image task (5.0)
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/v1/images/generations",
headers={
"Authorization": "Bearer " + os.environ["COMETAPI_KEY"],
"Content-Type": "application/json",
},
json={
"model": "seedream-5-0-260128",
"prompt": "A small blue origami bird on a white background, clean product illustration.",
"size": "2K",
"response_format": "url",
"async": True,
"watermark": False,
},
timeout=60,
)
response.raise_for_status()
result = response.json()
print(result["data"]["task_id"])
- lang: JavaScript
label: Async image task (5.0)
source: >
const response = await
fetch("https://api.cometapi.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "seedream-5-0-260128",
prompt: "A small blue origami bird on a white background, clean product illustration.",
size: "2K",
response_format: "url",
async: true,
watermark: false,
}),
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
console.log(result.data.task_id);
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication. Use your CometAPI key.
````