No longer supported
This model is legacy (released August 2022) and is no longer actively maintained or recommended by Stability AI. Consider using their current flagship model instead.
by Stability AI· Released August 2022· Cutoff 2022
Stable Diffusion 1.4 is a latent text-to-image diffusion model capable of generating photorealistic images from any text input. It was the first publicly released version of Stable Diffusion, trained on a subset of the LAION-5B dataset. This model marked a significant milestone in open-source AI image generation.
Input cost
Free (open source)
Output cost
Free (open source)
Context window
—
Max output
—
Modalities
Parameters
890M
License
CreativeML Open RAIL-M
General-purpose text-to-image generation with a focus on photorealism and creative exploration.
