The SDXL VAE is the variational autoencoder component used by Stability AI's Stable Diffusion XL model. It encodes images into a compressed latent representation and decodes them back to pixel space. This model can be used independently or integrated into custom diffusion pipelines via the Diffusers library.
Sdxl Vae sits in PulseGate's Image generation category. Efficiently compressing and reconstructing images in the latent space for diffusion models. Sdxl Vae is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API.
Stability AI builds and maintains Sdxl Vae, and it first shipped in 2021. The project is developed in the open on GitHub with 73.2k stars. Key capabilities include image encoding, image decoding, and latent space.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do