Stability AI
Stability AISpecializes in open-source generative AI models for image and text generation, including Stable Diffusion.
Total Models: 7
Stable-Diffusion-3.5-Large
Stable-Diffusion-3.5-Large

At 8.1 billion parameters, with superior quality and prompt adherence, this base model is the most powerful in the Stable Diffusion family. This model is ideal for professional use cases at 1 megapixel resolution. Stable Diffusion 3.5 Large produces diverse outputs, creating images that are represe

text-to-image
image-to-image
Stable-Image-Ultra
Stable-Image-Ultra

Powered by the advanced capabilities of Stable Diffusion 3.5 Large, Stable Image Ultra sets a new standard in photorealism. Stable Image Ultra is ideal for product imagery in marketing and advertising. It also excels in typography, dynamic lighting, and vibrant color rendering.

text-to-image
Stable-Image-Core
Stable-Image-Core

Leveraging an enhanced version of SDXL, Stable Image Core, delivers exceptional speed and efficiency while maintaining the highquality output synonymous with Stable Diffusion models.

text-to-image
stabilityai-stable-diffusion-xl-base-1-0
stabilityai-stable-diffusion-xl-base-1-0

SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model (available here: https://huggingface.co/stabilityai/stablediffusionxlbase1.0) is used to generate (noisy) latents, which

text-to-image
stabilityai-stable-diffusion-2-inpainting
stabilityai-stable-diffusion-2-inpainting

This stablediffusion2inpainting model is resumed from stablediffusion2base (512baseema.ckpt) and trained for another 200k steps. Follows the maskgeneration strategy presented in LAMA which

text-to-image
stabilityai-stable-diffusion-2-1
stabilityai-stable-diffusion-2-1

This stablediffusion21 model is finetuned from stablediffusion2 (768vema.ckpt) with an additional 55k steps on the same dataset (with punsafe=0.1), and then finetuned for another 155k extra steps with punsafe=0.98. The model

text-to-image
stabilityai-stable-diffusion-xl-refiner-1-0
stabilityai-stable-diffusion-xl-refiner-1-0

SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model (available here: https://huggingface.co/stabilityai/stablediffusionxlbase1.0) is used to generate (noisy) latents, which

image-to-image