---
title: "Generate or Edit Image"
method: POST
path: "/api/v1/flux/kontext/generate"
---

# Generate or Edit Image

`POST /api/v1/flux/kontext/generate`

Create a new image generation or editing task using the Flux Kontext AI model.

### Usage Modes
1. **Text-to-Image Generation**
   - Provide `prompt` and `aspectRatio`
   - Model will generate a new image based on the text description

2. **Image Editing**
   - Provide `prompt` and `inputImage`
   - You can optionally provide an `aspectRatio`.  
      - If supplied, the output will be cropped or padded to match this ratio.  
      - If omitted, the original image's ratio will be preserved.
   - Model will edit the input image according to the prompt

### Important Notes
- Generated images will expire after 14 days
- Prompts only support English
- Choose the appropriate model based on your needs:
  - flux-kontext-pro: Standard model for most use cases
  - flux-kontext-max: Enhanced model for complex scenes

## Request body

- object
  - `prompt` string, required — Text prompt describing the desired image or edit. Required for both generation and editing modes. - Should be detailed and specific - For image editing, describe the desired changes - For image generation, describe the complete scene - IMPORTANT: Only English language is supported
  - `enableTranslation` boolean — Whether to enable automatic translation feature. - Since prompt only supports English, when this parameter is true, the system will automatically translate non-English prompts to English - If your prompt is already in English, you can set this to false - Default value: true
  - `uploadCn` boolean — (Optional) Specifies the server region for image upload. Set to true to use servers in China, false to use non-China servers. Choose based on your geographical location for optimal upload speeds.
  - `inputImage` string, uri — URL of the input image for editing mode. Required when editing an existing image. - Must be a valid image URL - Image must be accessible to the API server
  - `aspectRatio` '21:9' | '16:9' | '4:3' | '1:1' | '3:4' | '9:16' — Output image aspect ratio. You Applicable in both text-to-image generation and image editing modes. For **text-to-image generation** , the output image will follow the specified aspect ratio. For **image editing** , if aspectRatio is provided, the edited image will follow that ratio. If not provided, the image will retain its original aspect ratio. Supported Aspect Ratios: | Ratio | Format Type | Common Use Cases | |-------|-------------|-----------------| | 21:9 | Ultra-wide | Cinematic displays, panoramic views | | 16:9 | Widescreen | HD video, desktop wallpapers | | 4:3 | Standard | Traditional displays, presentations | | 1:1 | Square | Social media posts, profile pictures | | 3:4 | Portrait | Magazine layouts, portrait photos | | 9:16 | Mobile Portrait | Smartphone wallpapers, stories | > Note: Default ratio is "16:9" if not specified.
  - `outputFormat` 'jpeg' | 'png' — Output image format.
  - `promptUpsampling` boolean — - If true, performs upsampling on the prompt - May increase processing time
  - `model` 'flux-kontext-pro' | 'flux-kontext-max' — Model version to use for generation. Available Options: | Model | Description | |--------------|-------------| | flux-kontext-pro | Standard model with balanced performance | | flux-kontext-max | Enhanced model with advanced capabilities | > Note: Choose flux-kontext-max for more demanding tasks that require higher quality and detail
  - `callBackUrl` string, uri — The URL to receive image generation or editing task completion updates. Optional but recommended for production use. - System will POST task status and results to this URL when image generation or editing completes - Callback includes generated image URLs and task information for both text-to-image and image editing operations - Your callback endpoint should accept POST requests with JSON payload containing image results - For detailed callback format and implementation guide, see [Image Generation/Editing Callbacks](./generate-or-edit-image-callbacks) - Alternatively, use the Get Image Details endpoint to poll task status
  - `safetyTolerance` 0 | 1 | 2 | 3 | 4 | 5 | 6 — **For Image Generation Mode:** Moderation level for inputs and outputs. Value ranges from 0 (most strict) to 6 (more permissive). **For Image Editing Mode:** Moderation level for inputs and outputs. Value ranges from 0 (most strict) to 2 (balanced). Default: 2
  - `watermark` string — Watermark identifier to add to the generated image. - Optional - If provided, a watermark will be added to the output image

## Response `200`

Request successful

- object
  - `code` 200 | 401 | 402 | 404 | 422 | 429 | 455 | 500 | 501 | 505 — Response status code - **200**: Success - Request has been processed successfully - **401**: Unauthorized - Authentication credentials are missing or invalid - **402**: Insufficient Credits - Account does not have enough credits to perform the operation - **404**: Not Found - The requested resource or endpoint does not exist - **422**: Validation Error - The request parameters failed validation checks - **429**: Rate Limited - Request limit has been exceeded for this resource - **455**: Service Unavailable - System is currently undergoing maintenance - **500**: Server Error - An unexpected error occurred while processing the request Server Error - The security tolerance level is out of range and should be 0-2 or 0-6 - **501**: Generation Failed - Image generation task failed - **505**: Feature Disabled - The requested feature is currently disabled
  - `msg` string — Error message when code != 200
  - `data` object
    - `taskId` string — Task ID, can be used with Get Image Details endpoint to query task status

## Other responses

- `500` — Server Error

---

[API](https://skmtc.dev/fluxapi/apis/common-api.md) · [All operations](https://skmtc.dev/fluxapi/apis/common-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/fluxapi/common-api/revisions/9751ebc7ccc9/schema)