curl --request POST \
--url https://gengen.farm/api/gengen/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "seedream-5-0-260128"
}
'import requests
url = "https://gengen.farm/api/gengen/v1/images/generations"
payload = { "model": "seedream-5-0-260128" }
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({model: 'seedream-5-0-260128'})
};
fetch('https://gengen.farm/api/gengen/v1/images/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"id": "image:550e8400-e29b-41d4-a716-446655440000",
"model": "seedream-5-0-260128",
"status": "succeeded",
"outputs": {
"images": [
"https://example.com/generated-image.jpeg"
]
}
}{
"error_code": "gengen.model_required",
"error_params": {
"field": "model"
},
"error": "A model is required"
}{
"error_code": "gengen.auth_required",
"error": "Missing Authorization bearer token"
}{
"error_code": "seedance.insufficient_balance",
"error": "Insufficient available balance"
}{
"error_code": "gengen.api_key_revoked",
"error": "GENGEN API key has been revoked"
}{
"error_code": "<string>",
"error_params": {
"failedAsset": {
"url": "<string>",
"field": "assets.referenceImages",
"index": 1,
"mediaType": "Image",
"stage": "validation"
}
},
"error": "<string>"
}Generate images
Generate one or more images synchronously. New integrations should use
normalized assets, controls, and providerOptions fields and read
generated media from outputs.images. The returned id identifies this
completed request for logs; it is not a task ID to poll.
curl --request POST \
--url https://gengen.farm/api/gengen/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "seedream-5-0-260128"
}
'import requests
url = "https://gengen.farm/api/gengen/v1/images/generations"
payload = { "model": "seedream-5-0-260128" }
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({model: 'seedream-5-0-260128'})
};
fetch('https://gengen.farm/api/gengen/v1/images/generations', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));{
"id": "image:550e8400-e29b-41d4-a716-446655440000",
"model": "seedream-5-0-260128",
"status": "succeeded",
"outputs": {
"images": [
"https://example.com/generated-image.jpeg"
]
}
}{
"error_code": "gengen.model_required",
"error_params": {
"field": "model"
},
"error": "A model is required"
}{
"error_code": "gengen.auth_required",
"error": "Missing Authorization bearer token"
}{
"error_code": "seedance.insufficient_balance",
"error": "Insufficient available balance"
}{
"error_code": "gengen.api_key_revoked",
"error": "GENGEN API key has been revoked"
}{
"error_code": "<string>",
"error_params": {
"failedAsset": {
"url": "<string>",
"field": "assets.referenceImages",
"index": 1,
"mediaType": "Image",
"stage": "validation"
}
},
"error": "<string>"
}Body
Normalized synchronous image generation request. Legacy Seedream request aliases remain accepted for existing clients, but new integrations should use the fields documented here.
Seedream model ID. Supported values:
dola-seedream-5-5-261028: Seedream 5.5.seedream-5-0-260128: Seedream 5.0 Lite.dola-seedream-5-0-pro-260628: Seedream 5.0 Pro.dola-seedream-5-0-flash-260915: Seedream 5.0 Flash.
dola-seedream-5-5-261028, seedream-5-0-260128, dola-seedream-5-0-pro-260628, dola-seedream-5-0-flash-260915 1"dola-seedream-5-5-261028"
Required for image generation; optional for layer decomposition. Without a decomposition prompt the model separates the major elements automatically. Recommended maximum: 300 Chinese characters or 600 English words. All models support Chinese and English; 5.5, Pro and Flash also support Russian, Arabic, Filipino, Thai, Turkish, Korean, Malay, Spanish, Portuguese, Indonesian, French, German, Vietnamese and Japanese.
Response
The synchronous generation completed successfully.
Standard response fields are listed first. Compatibility aliases can follow them for existing clients.