Edit images with AI models
June 3, 2025 (October 3, 2025)
Table of contents
This endpoint edits existing images using FLUX.1 Kontext, FLUX.1 Kontext Max, or Nano Banana / Gemini 2.5 Flash Image based on text prompts and reference images.
Model Capabilities
Parameter | FLUX.1 Kontextflux (default) | FLUX.1 Kontext Maxflux-premium | Nano Banana / Gemini 2.5 Flash Imagenano-banana |
---|---|---|---|
referenceAssetId | ✓ | ✓ | ✓ |
referenceAssetId2 | ✓ | ✓ | ✓ |
referenceAssetId3 | ✗ | ✓ | ✓ |
aspectRatio | ✓ | ✓ | ✗ |
https://api.useapi.net/v1/ltxstudio/images/edit
Request Headers
Authorization: Bearer {API token}
Content-Type: application/json
# Alternatively you can use multipart/form-data
# Content-Type: multipart/form-data
API token
is required, see Setup useapi.net for details.
Request Body
{
"prompt": "Add golden sunset lighting to the landscape",
"referenceAssetId": "asset:3b18…-type:image/png",
"aspectRatio": "16:9",
"shotType": "wide shot",
"shotAngle": "eye-level",
"seed": 123456
}
email
is optional when only one account configured. However, if you have multiple accounts configured, this parameter becomes required.prompt
is required, text description for image editing (max 2000 characters)referenceAssetId
is required, asset ID for the source image to edit. Use fieldfileId
from POST assets/?type=reference-image or GET assets/?filter=images.referenceAssetId2
is optional, second reference image asset ID.referenceAssetId3
is optional, third reference image asset ID (see model capabilities table above).location
is optional, location description for the image (max 2000 characters).weather
is optional, weather conditions description (max 2000 characters).lighting
is optional, lighting description (max 2000 characters).aspectRatio
is optional, output image aspect ratio (see model capabilities table above).
Supported values:16:9
,9:16
,1:1
.
Default:16:9
.shotType
is optional, type of shot for the image (e.g., “wide shot”, “close-up”, “medium shot”).shotAngle
is optional, camera angle for the shot.
Supported values:eye-level
,low-angle
,over-the-shoulder
,overhead
,birds-eye-view
.seed
is optional, random seed for reproducible results.model
is optional, the AI model to use for image editing.
Supported values:flux
,flux-premium
,nano-banana
.
Default:flux
.pollForResult
is optional, number of polling attempts to wait for completion (each attempt waits 3 seconds, up to 60 seconds total max) before sending job to the scheduler. For example,pollForResult: 5
will poll every 3 seconds for up to 15 seconds total. Supported values:1
-20
. Default: immediate return withjobId
.maxJobs
is optional, override the default maximum number of concurrent jobs.replyUrl
is optional, webhook URL for job completion notifications.
See GET assets/jobId
for response model.replyRef
is optional, custom reference for webhook identification.
Responses
-
{ "jobId": "email:[email protected]:7a34b821-9fd0-205e-d21b-4abc6f7839e7-type:image", "generationId": "gen_abc123def456" }
-
200 OK (pollForResult completed)
{ "status": { "type": "completed", "progress": 100, "artifact": { "assetUrl": "https://storage.googleapis.com/lt-infinity-prd/artifacts/vertex-ai/…", "expirationDateString": "1748919477350", "asset": { "type": "artifact", "fileId": "asset:3b18…-type:image/png", "mimeType": "image/png", "artifactSubtype": "vertex-ai" } } }, "jobId": "email:[email protected]:7a34b821-9fd0-205e-d21b-4abc6f7839e7-type:image", "replyRef": "custom-reference-123", "replyUrl": "https://webhook.example.com/ltx-callback", "code": 200 }
-
{ "error": "Error message", "code": 400 }
-
{ "error": "Unauthorized", "code": 401 }
-
{ "error": "Insufficient credits", "code": 402 }
Model
Use GET assets/jobId
to retrieve job status and results if they were not provided with the response.
{ // TypeScript, all fields are optional
status: {
type: 'active' | 'completed' | 'failed'
progress?: number
message?: string
artifact?: {
assetUrl: string
expirationDateString: string
asset: {
type: string
fileId: string
mimeType: string
artifactSubtype: string
}
}
}
jobId?: string
generationId?: string
replyRef?: string
replyUrl?: string
code?: number
}
Examples
-
curl "https://api.useapi.net/v1/ltxstudio/images/edit" \ -H "Authorization: Bearer …" \ -H "Content-Type: application/json" \ -d '{ "prompt": "Add golden sunset lighting to the landscape", "referenceAssetId": "asset:3b18…-type:image/png", "aspectRatio": "16:9", "shotType": "wide shot", "shotAngle": "eye-level", "pollForResult": 10 }'
-
const token = "API token"; const apiUrl = "https://api.useapi.net/v1/ltxstudio/images/edit"; const response = await fetch(apiUrl, { method: "POST", headers: { "Authorization": `Bearer ${token}`, "Content-Type": "application/json", }, body: JSON.stringify({ "prompt": "Add golden sunset lighting to the landscape", "referenceAssetId": "asset:3b18…-type:image/png", "aspectRatio": "16:9", "shotType": "wide shot", "shotAngle": "eye-level", "pollForResult": 10 }) }); const result = await response.json(); console.log("response", {response, result});
-
import requests token = "API token" apiUrl = "https://api.useapi.net/v1/ltxstudio/images/edit" headers = { "Authorization" : f"Bearer {token}", "Content-Type": "application/json" } data = { "prompt": "Add golden sunset lighting to the landscape", "referenceAssetId": "asset:3b18…-type:image/png", "aspectRatio": "16:9", "shotType": "wide shot", "shotAngle": "eye-level", "pollForResult": 10 } response = requests.post(apiUrl, headers=headers, json=data) print(response, response.json())