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.
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.
text prompt
Num Images
number of images to generate (Default: 1, 1 ≤ num_images ≤ 4)
Num Inference Steps
number of denoising steps (Default: 1, 1 ≤ num_inference_steps ≤ 10)
Guidance Scale
classifier-free guidance, higher means follow prompt more closely (Default: 7.5, 1 ≤ guidance_scale ≤ 20)
image width in px 13
image height in px 13
random seed, empty means random (Default: empty, 0 ≤ seed)
You need to login to use this model
FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post.
FLUX.1 [schnell]
can generate high-quality images in only 1 to 4 steps.apache-2.0
licence, the model can be used for personal, scientific, and commercial purposes.The model and its derivatives may not be used