> ## Documentation Index
> Fetch the complete documentation index at: https://docs.maxapi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Image generation

> Browse image generation, editing, and visual processing endpoints.

Image APIs include OpenAI-compatible endpoints, provider-native generation APIs, and asynchronous visual utilities. Choose an API family based on your client and required controls.

## Common entry points

| Use case                  | Recommended entry point                        | Result                       |
| ------------------------- | ---------------------------------------------- | ---------------------------- |
| General text-to-image     | `POST /v1/images/generations`                  | Image URL or Base64          |
| Image editing             | `POST /v1/images/edits`                        | Image URL or Base64          |
| Gemini image generation   | `POST ...:generateContent`                     | `candidates[].content.parts` |
| Stable Image              | `/sd/v2beta/stable-image/generate/*`           | Binary image or Base64 JSON  |
| Segmentation, repair, OCR | `/api/tasks/visual/*`, `/api/tasks/document/*` | Asynchronous task            |

## Choose an API family

<CardGroup cols={2}>
  <Card title="Compatible formats" icon="braces">OpenAI Images and Gemini generateContent.</Card>
  <Card title="Specialized image models" icon="sparkles">Stability AI, Ideogram, Midjourney, and MewXAI.</Card>
  <Card title="Visual utilities" icon="wand-magic-sparkles">Upscale, segment, repair, colorize, compress, and OCR.</Card>
  <Card title="Async results" icon="clock" href="/en/guides/async-tasks">Submit a task and retrieve the result by its ID.</Card>
</CardGroup>

<Warning>
  File upload endpoints use the `multipart/form-data` fields shown on their endpoint pages. Do not reuse a JSON body for a file upload endpoint.
</Warning>