Text-to-image generation AI launched by StabilityAI
What is Stable Diffusion?
Stable Diffusion is an AI text-to-image generation model based on deep learning, released in 2022. The model is primarily used to generate detailed images and illustrations based on textual descriptions. It was developed by the startup company StabilityAI in collaboration with some academic researchers and non-profit organizations.
Stable Diffusion is a type of Latent Diffusion Model, which is a deep generative neural network. The code and model weights of Stable Diffusion have been publicly released and can be run on most computer hardware equipped with moderate GPUs. This stands in contrast to previous proprietary text-to-image models (such as DALL·E and Midjourney), which could only be accessed through cloud computing services.
The online versions of Stable Diffusion can primarily be accessed through the following official websites:
- DreamStudio版（officially launched by StabilityAI）
- Stable Diffusion XL （launched under StabilityAI's ClipDrop）
- Stable Artisan（Discord version service launched by StabilityAI）
