flux-pro
Model Overview
This is first version of Flux Pro, but it generates images of unmatched quality, outperforming popular models like Midjourney v6.0, DALL·E 3 (HD), and SD3-Ultra.
You can also view a detailed comparison of this model on our main website.
flux-pro
Format: JPEG, PNG Min size: 256x256 Max size: 1440x1440 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
landscape_4_3
The size of the generated image.
The number of inference steps to perform.
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.
The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.
2
Possible values: The format of the generated image.
jpeg
Possible values: The text prompt describing the content, style, or composition of the image to be generated.
1
The same seed and the same prompt given to the same version of the model will output the same image every time.
POST /v1/images/generations HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer <YOUR_AIMLAPI_KEY>
Content-Type: application/json
Accept: */*
Content-Length: 178
{
"model": "flux-pro",
"image_size": "landscape_4_3",
"num_inference_steps": 1,
"guidance_scale": 1,
"safety_tolerance": "2",
"output_format": "jpeg",
"prompt": "text",
"num_images": 1,
"seed": 1
}
No content
Quick Example
Let's generate an image of the specified size using a simple prompt.
The maximum value for both width and height is 1440
, and the minimum is 256
.
The value must be a multiple of 32.
import requests
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={
"prompt": "Rabbit singing",
"model": "flux-pro",
'image_size': {
"width": 1024,
"height": 320
}
}
)
response.raise_for_status()
data = response.json()
print("Generation:", data)
if __name__ == "__main__":
main()
We obtained the following nice 1024x320 image by running this code example:

"Rabbit singing"
Last updated
Was this helpful?