# Nano Series Image Generation

This file is the focused AI-readable context for one UniAll documentation page.

URL: https://docs.uniall.ai/models/image/nano-series
Locale: en
Markdown: https://docs.uniall.ai/ai/pages/models/image/nano-series.md
Description: Generate or edit images with NanoBanana family models through UniAll image APIs.

Agent guidance:
- Use this page when the user is asking about this specific route or model capability.
- Preserve endpoint paths, JSON keys, model IDs, and placeholder values exactly.
- Treat examples such as `sk-***`, `{BASE_URL}`, and `task_xxx` as safe placeholders, not real secrets.

## Page Markdown

Nano Series covers the NanoBanana family. Use it when you need a concrete Nano model tier and `aspect_ratio`-based shape control. The source scope includes both OpenAI-compatible and Gemini-compatible entry points, but new general integrations can start from the async image task flow.

## Supported Models

| Model family | Example IDs | Notes |
| --- | --- | --- |
| NanoBanana | `NanoBanana` | Base NanoBanana model. |
| NanoBanana Pro | `NanoBananaPro-*` | Pro tier variants. |
| NanoBanana 2 | `NanoBanana2-0.5K`, `NanoBanana2-1K` | Resolution-tiered NanoBanana 2 variants. |

Actual availability depends on account channel and model-price configuration.

## Recommended Endpoint

```http
POST /v1/images/tasks
GET  /v1/images/tasks/{task_id}
```

The Apifox source also exposes OpenAI-compatible image endpoints for Nano:

```http
POST /v1/images/generations
POST /v1/images/edits
```

and a Gemini-compatible format for Gemini-style clients. Use the format that matches your client. The request concepts below stay the same.

## Authentication

```http
Authorization: Bearer sk-***
Content-Type: application/json
```

## Request Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `model` | string | Yes | Concrete Nano model ID, such as `NanoBanana2-0.5K`. |
| `prompt` | string | Yes | Generation or editing prompt. |
| `task_type` | string | No | `text2image` or `image2image`. Can be inferred from image input. |
| `image` | string/object | Conditional | Single reference image for editing. |
| `images` | string[] | Conditional | Multiple reference image URLs. |
| `aspect_ratio` | string | No | Recommended shape control, such as `1:1`, `16:9`, `9:16`, `4:3`, or `3:4`. |
| `output_format` | string | No | `NanoBanana` supports `png`, `jpeg`, `webp`; Pro and NanoBanana 2 variants support `png` and `jpeg` in the current source scope. |
| `n` | integer | No | Output count. Default is `1`; maximum depends on upstream limits. |
| `response_format` | string | No | Prefer `url`. |

## Text-To-Image Example

```bash
curl -X POST "{BASE_URL}/v1/images/tasks" \
  -H "Authorization: Bearer sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "NanoBanana2-0.5K",
    "task_type": "text2image",
    "prompt": "A small red cube on a clean white desk, minimal product photo, soft daylight",
    "aspect_ratio": "1:1",
    "output_format": "png",
    "n": 1,
    "response_format": "url"
  }'
```

## Image-To-Image Example

```bash
curl -X POST "{BASE_URL}/v1/images/tasks" \
  -H "Authorization: Bearer sk-***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "NanoBanana2-0.5K",
    "task_type": "image2image",
    "prompt": "Turn the reference image into a clean product render",
    "image": "https://example.com/input.png",
    "aspect_ratio": "16:9",
    "output_format": "jpeg",
    "n": 1,
    "response_format": "url"
  }'
```

## Query Task Status

```bash
curl "{BASE_URL}/v1/images/tasks/task_xxx" \
  -H "Authorization: Bearer sk-***"
```

```json
{
  "code": "success",
  "message": "",
  "data": {
    "task_id": "task_xxx",
    "status": "succeeded",
    "progress": "100%",
    "result_url": "https://example.com/result.png",
    "metadata": {
      "task_type": "text2image",
      "result_count": 1
    },
    "error": null
  }
}
```

## Billing Notes

NanoBanana family models are billed by configured model unit price multiplied by `n` or the actual returned result count. `aspect_ratio` and `output_format` control output shape and format, but are not separate billing dimensions in the current source scope.

## Common Errors

- Passing a Nano model ID that is not enabled for the current account.
- Mixing `image` and `images` with compatibility image fields.
- Treating `size` as the primary Nano control; use `aspect_ratio` instead.
- Requesting an unsupported output format for the selected Nano family.
- Polling before the task has been created.

## Related Pages

- [Async Image Generation](/models/image/async-image-generation)
- [GPT-Image-2 Image Generation](/models/image/gpt-image-2)
- [Seedream Image Generation](/models/image/seedream)