POST
v1
/
replicate
/
imagegeneration
curl --request POST \
  --url http://localhost:9000/api/v1/replicate/imagegeneration \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "prompt": "<string>",
  "width": 123,
  "height": 123,
  "scheduler": "<string>",
  "num_outputs": 123,
  "guidance_scale": 123,
  "negative_prompt": "<string>",
  "num_inference_steps": 123
}'

​
Query

​
model
string
default:
"bytedance/sdxl-lightning-4step"
required

The image model to be used;

​
Body

​
prompt
string
required

Input prompt

​
width
int
default:
"1024"

Width of output image. Recommended 1024 or 1280

​
height
int
default:
"1024"

Height of output image. Recommended 1024 or 1280

​
scheduler
string
default:
"K_EULER"

scheduler

​
num_outputs
int
default:
"1"

Number of images to output.

​
guidance_scale
float
default:
"0.0"

Scale for classifier-free guidance. Recommended 7-8

​
negative_prompt
string

Negative Input prompt

​
num_inference_steps
int
default:
"4"

Number of denoising steps. 4 for best results

Was this page helpful?

Suggest editsRaise issue
Introductionv1/replicate/imagegeneration