POST
/
api
/
v1
/
client
/
img2img
Image to Image
curl --request POST \
  --url http://localhost:8000/api/v1/client/img2img \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form image='@example-file' \
  --form 'prompt=<string>' \
  --form model=Flux_2_Klein_4B_BF16 \
  --form steps=123 \
  --form seed=123 \
  --form 'images[]=<string>' \
  --form 'negative_prompt=<string>' \
  --form width=123 \
  --form height=123 \
  --form guidance=123 \
  --form 'loras=<string>' \
  --form 'webhook_url=<string>' \
  --form images[].items='@example-file'
{
  "data": {
    "request_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

Authorizations

Authorization
string
header
required

API key obtained from the ModelBeam dashboard

Body

multipart/form-data
image
file
required

Source image file (max 10MB). Mutually exclusive with images[]

prompt
string
required

Text description for transformation

model
string
required

Model slug

Example:

"Flux_2_Klein_4B_BF16"

steps
integer
required

Number of inference steps

seed
integer
required

Random seed

images[]
file[]

Multiple source images. Mutually exclusive with image

negative_prompt
string

What to avoid

width
integer

Output width

height
integer

Output height

guidance
number

CFG scale

loras
string

JSON-encoded array of LoRA objects

webhook_url
string

HTTPS webhook URL

Maximum string length: 2048

Response

Transformation job created

data
object