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

# FLUX.2 [flex]

> FLUX.2 [flex] text-to-image model by Black Forest Labs via Anyfast API.

FLUX.2 \[flex] is a highly configurable text-to-image generation model from Black Forest Labs, available through Anyfast. It offers fine-grained control over inference steps and guidance scale for design experts. The API is **synchronous** — it returns the generated image directly as base64-encoded data.

## Key capabilities

* **Text-to-image** — Generate images from text descriptions
* **Inference steps control** — Adjust sampling steps (1–50) for speed vs. fidelity tradeoff
* **Guidance scale** — Fine-tune prompt adherence (1.5–10)
* **High resolution** — Supports up to 4MP output resolution
* **Reproducible** — Use `seed` for deterministic generation

## Quick example

<CodeGroup>
  ```bash cURL theme={null}
  curl https://www.anyfast.ai/v1/images/generations \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "flux-2-flex",
      "prompt": "A cute baby polar bear",
      "size": "1024x1024",
      "inference_steps": 30,
      "guidance_scale": 7.5
    }'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "https://www.anyfast.ai/v1/images/generations",
      headers={"Authorization": "Bearer YOUR_API_KEY"},
      json={
          "model": "flux-2-flex",
          "prompt": "A cute baby polar bear",
          "size": "1024x1024",
          "inference_steps": 30,
          "guidance_scale": 7.5
      }
  )

  result = response.json()
  # result["data"][0]["b64_json"] contains the base64-encoded image
  ```
</CodeGroup>

## Parameters

| Parameter         | Type    | Required | Description                                                                           |
| ----------------- | ------- | -------- | ------------------------------------------------------------------------------------- |
| `model`           | string  | Yes      | Must be `flux-2-flex`                                                                 |
| `prompt`          | string  | Yes      | Text description of the image                                                         |
| `n`               | integer | No       | Number of images (1–4). Default: `1`                                                  |
| `size`            | string  | No       | Output size, e.g. `1024x1024`. Supports up to 4MP                                     |
| `inference_steps` | integer | No       | Sampling steps (1–50). Low (6–20) for fast prototyping, high (40–50) for max fidelity |
| `guidance_scale`  | number  | No       | Guidance scale (1.5–10). Higher = more prompt-faithful                                |
| `output_format`   | string  | No       | `jpeg` or `png`                                                                       |
| `seed`            | integer | No       | Random seed for reproducibility                                                       |

## Response

| Field             | Description               |
| ----------------- | ------------------------- |
| `data[].b64_json` | Base64-encoded image data |
| `created`         | Unix timestamp            |

<Card title="API Reference" icon="code" href="/api-reference/model-api/blackforestlabs/flux-2-flex">
  View the interactive API playground for FLUX.2 \[flex].
</Card>

<script src="/feedback.js" />