Skip to main content
POST
/
v3
/
async
/
glm-image
GLM Image Generation
curl --request POST \
  --url https://api.novita.ai/v3/async/glm-image \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "size": "<string>",
  "prompt": "<string>",
  "quality": "<string>",
  "watermark_enabled": true
}
'
{
  "task_id": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://novita.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

GLM Image text-to-image generation tool creates high-quality images from text prompts, producing HD images with fine details and high consistency.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
size
string
default:"1280x1280"
Image size. Recommended values: 1280x1280 (default), 1568x1056, 1056x1568, 1472x1088, 1088x1472, 1728x960, 960x1728. Custom sizes: dimensions should be 1024-2048px, max total pixels 4194304, both must be multiples of 32.
​
prompt
string
required
Text description of desired image. Describe the scene, subject, style, and details you want in the generated image.
​
quality
string
default:"hd"
Image quality. HD produces finer details with higher consistency.Optional values: hd
​
watermark_enabled
boolean
default:true
Control AI watermark on generated images. true: Enable watermark (default). false: Disable watermark

​
Response

​
task_id
string
required
Use the task_id to request the Task Result API to retrieve the generated outputs.