flux/srpo/text-to-image

This documentation is valid for the following list of our models:

  • flux/srpo

Model Overview

flux/dev model upgraded with Tencent’s SRPO technique.

Model
Generated image properties

flux/srpo

Format: PNG Min size: 512x512 Max size: 1536x1536 Default size: 1024x768 For both height and width, the value must be a multiple of 32.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post
Authorizations
Body
modelundefined · enumRequiredPossible values:
image_sizeany ofOptionalDefault: landscape_4_3
or
string · enumOptional

The size of the generated image.

Possible values:
num_inference_stepsinteger · min: 1 · max: 50Optional

The number of inference steps to perform.

Default: 28
guidance_scalenumber · min: 1 · max: 20Optional

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.

Default: 4.5
sync_modebooleanOptional

If set to true, the function will wait for the image to be generated and uploaded before returning the response. This will increase the latency of the function but it allows you to get the image directly in the response without going through the CDN.

Default: false
enable_safety_checkerbooleanOptional

If set to True, the safety checker will be enabled.

Default: true
output_formatstring · enumOptional

The format of the generated image.

Default: jpegPossible values:
accelerationstring · enumOptional

The speed of the generation. The higher the speed, the faster the generation.

Default: regularPossible values:
promptstring · max: 4000Required

The text prompt describing the content, style, or composition of the image to be generated.

num_imagesnumber · min: 1 · max: 4Optional

The number of images to generate.

Default: 1
seedinteger · min: 1Optional

The same seed and the same prompt given to the same version of the model will output the same image every time.

Responses
201

Successfully generated image

application/json
post
async function main() {
  const response = await fetch('https://api.aimlapi.com/v1/images/generations', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'flux/srpo',
      prompt: 'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.',
    }),
  });

  const data = await response.json();
  console.log(JSON.stringify(data, null, 2));
}

main();
201

Successfully generated image

{
  "data": [
    {
      "url": "text",
      "b64_json": "text"
    }
  ]
}

Quick Example

Let's generate an image using a simple prompt.

import requests
import json  # for getting a structured output with indentation

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
            "model": "flux/srpo",
            "prompt": "A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.",
            "image_size": {
                "width": 1440,
                "height": 512
            }  
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))

if __name__ == "__main__":
    main()
Response
{
  "images": [
    {
      "url": "https://cdn.aimlapi.com/eagle/files/zebra/GtH4bTLhiXD7YTwYAlO21.jpeg",
      "width": 1440,
      "height": 512,
      "content_type": "image/jpeg"
    }
  ],
  "timings": {
    "inference": 0.747110141441226
  },
  "seed": 490733907,
  "has_nsfw_concepts": [
    false
  ],
  "prompt": "A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.",
  "data": [
    {
      "url": "https://cdn.aimlapi.com/eagle/files/zebra/GtH4bTLhiXD7YTwYAlO21.jpeg",
      "width": 1440,
      "height": 512,
      "content_type": "image/jpeg"
    }
  ],
  "meta": {
    "usage": {
      "tokens_used": 52500
    }
  }
}

We obtained the following 1440x512 image by running this code example:

'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.'

Last updated

Was this helpful?