Stability AI releases Stable Diffusion 2.0 as open source
Stability AI released Stable Diffusion 2.0 with a new text encoder, 512- and 768-pixel generation models, and several image-editing models.
What happened
Event details
Stability AI released Stable Diffusion 2.0 as open source on November 24, 2022. The family used an OpenCLIP text encoder and included text-to-image models with default 512×512 and 768×768 output, along with depth-conditioned generation, 4× super-resolution, and inpainting models. Code and model access were available on the release date.
Assessment
Why it matters
Stable Diffusion 2.0 expanded the resolution and conditioning capabilities of the open image-generation ecosystem while retaining local model deployment.
Availability
Access notes
Code and model weights were public. API and DreamStudio availability were planned for the following days.