Seedance 2.0 Mini is live on viddly.io — video from $0.045/second 🚀
viddly.ioAI Model Gateway
API Market
Black Forest Labs

Flux 2 Kontext API

Instruction-based editing that preserves identity

Change one thing and leave the rest alone — the model most likely to keep a product or face pixel-consistent.

Image editingIdentity preservationInpainting

Quickstart

Authenticate with a bearer token from your dashboard, then POST the request below.

curl -X POST https://api.viddly.io/v1/images/generations \
  -H "Authorization: Bearer $VIDDLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2-kontext",
    "prompt": "a lighthouse in a storm, drone orbit, dusk",
    "size": "1024x1024",
    "num_images": 1
  }'

Parameters

NameTypeDefaultDescription
prompt*textWhat to generate. Describe subject, action, camera and lighting.
image_urlimageOptional reference or first-frame image. Publicly reachable URL.
sizeenum1024x1024 | 1536x1024 | 2048x20481024x1024Output dimensions.
num_imagesnumber1How many images to return (1–4).
seednumberFix for reproducible results.

Similar models