No longer supported
This model is legacy (released December 2022) and is no longer actively maintained or recommended by Stability AI. Consider using their current flagship model instead.
by Stability AI· Released December 2022
Stable Diffusion 2.1 is a text-to-image diffusion model that generates high-quality images from natural language prompts. It improves upon Stable Diffusion 2.0 with better aesthetic quality and reduced NSFW content filtering. This model is part of the Stable Diffusion 2.x series, which introduced a new text encoder (OpenCLIP) and higher resolution (768x768) capabilities.
Input cost
Free (open source)
Output cost
Free (open source)
Context window
—
Max output
—
Modalities
Parameters
~1.5B (UNet) + ~1.2B (text encoder)
License
CreativeML Open RAIL-M
High-quality image generation from text prompts with improved aesthetics and reduced censorship.
