POST
v1
/
replicate
/
imagegeneration
curl --request POST \
  --url http://localhost:9000/api/v1/replicate/imagegeneration \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'prompt=<string>' \
  --form width=123 \
  --form height=123 \
  --form num_outputs=123 \
  --form 'negative_prompt=<string>' \
  --form num_inference_steps=123 \
  --form 'scheduler=<string>' \
  --form guidance_scale=123 \
  --form prompt_strength=123 \
  --form lora_scale=123 \
  --form apply_watermark=true

​
Query

​
model
string
default:"lorenzomarines/astra"
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

​
num_outputs
int
default:"1"

Number of images to output.

​
negative_prompt
string

Negative Input prompt

​
num_inference_steps
int
default:"50"

Number of denoising steps.

​
scheduler
string
default:"K_EULER"

scheduler

​
guidance_scale
float
default:"7.0"

Scale for classifier-free guidance

​
prompt_strength
float
default:"0.8"

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

​
lora_scale
float
default:"0.6"

LoRA additive scale. Only applicable on trained models.

​
apply_watermark
boolean
default:"false"

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

​
image
file

Input image for img2img or inpaint mode

​
mask
file

Input image for img2img or inpaint mode