# Tencent | Flux 1 | Srpo | Text to Image

FLUX.1 SRPO [dev] is a 12B-parameter flow transformer fine-tuned with Semantic Relative Preference Optimization, designed to generate highly realistic and visually appealing images from text prompts. It delivers strong aesthetic quality and consistency.

## API Information

- **Model Slug:** tencent-flux-1-srpo-text-to-image
- **Branded URL:** https://www.eachlabs.ai/black-forest-labs/flux-tencent/tencent-flux-1-srpo-text-to-image
- **Provider:** Black Forest Labs
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.00000000
- **Estimated Processing Time:** 6 seconds
- **Last Updated:** 2026-06-04
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/tencent-flux-1-srpo-text-to-image

## Pricing

- **Charge Type:** dynamic

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | ceil(image_pixel_count / 1048576) * num_images * 0.025 |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The prompt to generate an image from. |
| image_size | string | No | landscape_4_3 | square_hd,square,portrait_4_3,portrait_16_9,landscape_4_3,landscape_16_9 | The size of the generated image. |
| num_inference_steps | integer | No | 28 | 1–50 | The number of inference steps to perform. |
| seed | string | No | - | - | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| guidance_scale | number | No | 4.5 | 1–20 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| num_images | integer | No | 1 | 1–4 | The number of images to generate. |
| enable_safety_checker | boolean | No | true | - | If set to true, the safety checker will be enabled. |
| output_format | string | No | jpeg | jpeg,png | The format of the generated image. |
| acceleration | string | No | regular | none,regular,high | The speed of the generation. The higher the speed, the faster the generation. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tencent-flux-1-srpo-text-to-image",
  "input": {
    "prompt": "Female explorer, athletic build, trail-hardened presence, focused eyes, technical outdoor gear with backpack and trekking poles, desert canyon cliffs background, golden hour lighting, dynamic leading stance, sun-kissed skin with tousled long hair, determined face with calm authority, seasoned adventurer aura"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**tencent-flux-1-srpo-text-to-image — Text-to-Image AI Model**

Transform detailed text prompts into highly realistic, visually stunning images with **tencent-flux-1-srpo-text-to-image**, a cutting-edge text-to-image AI model from Black Forest Labs' flux-tencent family. This 12B-parameter flow transformer, fine-tuned using Semantic Relative Preference Optimization (SRPO), excels at delivering exceptional aesthetic quality and prompt adherence, solving the common issue of generic or inconsistent outputs in standard diffusion models. Developers and creators searching for a **Black Forest Labs text-to-image** solution find tencent-flux-1-srpo-text-to-image ideal for generating photorealistic visuals with superior consistency, supporting high-resolution outputs up to 1024x1024 and various aspect ratios for flexible applications.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.