flux-realism
Last updated
Was this helpful?
Last updated
Was this helpful?
A state-of-the-art model designed to generate photorealistic images from textual descriptions. It allows users to create lifelike visuals without the need for extensive realism-related prompts.
flux-realism
Format: JPEG, PNG Min size: 512x512 Max size: 1536x1536 Default size: 1024x768 For both height and width, the value must be a multiple of 32.
If you don’t have an API key for the AI/ML API yet, feel free to use our .
Let's generate an image of the specified size using a simple prompt.
The maximum value for both width and height is 1536
, and the minimum is 512
.
The value must be a multiple of 32.
We obtained the following 1472x512 image by running this code example. The textures look significantly more realistic compared to the earlier FLUX models.
We were also curious how the model would perform with more large-scale scenes. Here's what we got with the prompt 'Epic battle of spaceships'
.
landscape_4_3
The size of the generated image.
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 number of inference steps to perform.
If set to True, the safety checker will be enabled.
true
The format of the generated image.
jpeg
Possible values: The text prompt describing the content, style, or composition of the image to be generated.
The number of images to generate.
1
The same seed and the same prompt given to the same version of the model will output the same image every time.
No content
'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.'
'Epic battle of spaceships'