Use o CometAPI POST /v1/images/generations para geração Seedream de texto para imagem e de imagem para imagem — com suporte a saída sequencial de múltiplas imagens e imagens de referência.
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'{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"size": "<string>"
}
],
"usage": {
"generated_images": 123,
"output_tokens": 123,
"total_tokens": 123
},
"model": "<string>"
}/v1/images/generations. Compatível com geração text-to-image e image-to-image.
Para ver a lista completa de modelos, consulte a página de modelos. Para a documentação detalhada dos parâmetros do provedor, consulte a documentação da VolcEngine.
sequential_image_generation como auto e, opcionalmente, configure sequential_image_generation_options.max_images para limitar o número de imagens geradas. O total de imagens de referência mais imagens geradas deve ser ≤ 15.image (array de URLs ou data URIs em base64) junto com um prompt de texto. Suporta até 14 imagens de referência.
url retornada é um link assinado de armazenamento de objetos que contém & e outros caracteres especiais.\{"Code":"AccessDenied","Message":"Access Denied","EC":"0003-00000015"\}
| jq -r '.data[].url' para extrair a URL corretamente.result.data[0].url ou image["url"] — a string já está completa; passe-a diretamente para requests.get() ou webbrowser.open().result.data[0].url.& e % na URL não sejam truncados nem recebam escape duplo.Bearer token authentication. Use your CometAPI key.
Parameters for Seedream image generation (text-to-image and image-to-image).
Model to use. See the Models page for current Seedream model IDs.
Text prompt describing the image to generate. Supports both Chinese and English. Recommended max 300 Chinese characters or 1000 English characters.
Output format. url returns a temporary image link (valid for 24 hours); b64_json returns base64-encoded image data.
url, b64_json Output resolution. Presets 2K, 4K, or exact pixels like 2048x2048, 2304x1728, 2848x1600, 1600x2848, etc. Default: 2048x2048.
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.
When true, adds an 'AI Generated' watermark to the bottom-right corner of the output image.
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).
Random seed for reproducible outputs. Range: -1 to 2147483647. Use -1 (default) for random generation. Legacy parameter — ignored by newer models.
Controls sequential (multi-image) generation mode.
auto: model decides whether to generate a sequence based on the promptdisabled: always generate a single imageauto, disabled Configuration for sequential (multi-image) generation. Only effective when sequential_image_generation is auto.
Show child attributes
Output image file format. Options: png, jpeg.
png, jpeg Successful Response
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'{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"size": "<string>"
}
],
"usage": {
"generated_images": 123,
"output_tokens": 123,
"total_tokens": 123
},
"model": "<string>"
}