Models

Kiara Edit Base

Stable

Scene composite. Drop in one reference (or up to three — character 1, character 2, optional pose anchor) and write the scene + action. With a single reference it edits that subject into the new scene; with multiple it composes them together. Source dimensions preserved with a 4K finish.

Product id

kiara-edit

Price

$0.05 / call

Output

image (jpeg)

Avg latency

~120s

Parameters

Inputs

Send these in the JSON body of a POST /v1/generations request alongside "product": "kiara-edit".

source_image_urlurlRequired

HTTPS URL to the primary input image this model transforms. Must be publicly reachable for the duration of the job.

promptstringRequired

Text prompt that describes what to generate. 1–4000 characters. Be specific — subject, lighting, lens, mood, action.

second_image_urlurlOptional

HTTPS URL to an optional second reference image (e.g. a face, outfit, or pose source).

pose_image_urlurlOptional

HTTPS URL to an optional pose reference image.

seedintegerOptional0 – 4,294,967,295

Deterministic seed. Same seed + same prompt = same image. Omit for a random seed.

webhook_urlurlOptional

HTTPS callback fired when the job reaches a terminal state. HMAC-SHA256 signed. See the Webhooks guide.

metadataobjectOptional

Arbitrary JSON object echoed back on retrieval and in the webhook. Useful for correlating jobs to your records. ≤ 4 KB.

POST /v1/generations — full reference for the create endpoint.
Playground — try this model inline with your key.

Quick call

POSTKiara Edit Base/v1/generations

curl https://api.kiara-api.com/v1/generations \
  -H "Authorization: Bearer $KIARA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "product": "kiara-edit",
       "source_image_url": "https://example.com/source.jpg",
       "prompt": "your prompt here"
     }'