Sign up
Log in
Sign up
Log in
Home
Models
Text to Image

Stable Diffusion 1.5 (accelerated)

A deep learning model capable of generating photo-realistic images based on text input. You can run the world’s fastest and cheapest Stable Diffusion endpoint today in OctoAI.

Run Model
Sign Up to Fine-Tune Stable Diffusion

Advice from ML Experts

Different samplers can give slightly different perceptual qualities to your images and can vary in the number of steps to create a good image. The "DPM" family of schedulers can get good images in 20 - 25 steps so can be used for quick iteration and prompt tuning. By saving the seed used to generate your initial images, you can always rerun the same job with a higher number of steps to get a more refined image.

Input

Scheduler

Output

Generated in: XX ms

Run Time & Costs

OctoAI brings you the fastest Stable Diffusion available today. Internal benchmarking, run against creation of 512x512 images with 30 steps shows image generation latency under 1.5 seconds when running on the A10G tier, and under 0.7 seconds on the A100 tier. Detailed benchmarking is in progress, and additional performance data will be updated here once available.

Model Information

@InProceedings {Rombach_2022_CVPR,
  author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},

  title = {High-Resolution Image Synthesis With Latent Diffusion Models},

  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},

  month = {June},

  year = {2022},

  pages = {10684-10695}

}