black-forest-labs/FLUX-1-schnell
FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. This model offers cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.
Try the model with a sample request using the same API shape shown in the reference page.
number of denoising steps (Default: 1, 1 ≤ num_inference_steps ≤ 50)
image width in px (Default: 1024, 128 ≤ width ≤ 1920)
image height in px (Default: 1024, 128 ≤ height ≤ 1920)
Text prompt describing the image
number of images to generate (Default: 1, 1 ≤ num_images ≤ 4)
random seed, empty means random (Default: empty, 0 ≤ seed < 18446744073709552000)
Adjust settings and run the demo to see the model output generated here in real-time.
