SD XL v1.0 VAE fix

1

Design

Runware

SDXL

Pro

A diffusion-based text-to-image generative model developed by Stability AI, designed to generate and modify images based on text prompts. The model uses a two-step pipeline involving a base model and a high-resolution model to produce high-quality visuals. It employs two fixed, pretrained text encoders, OpenCLIP-ViT/G and CLIP-ViT/L, to interpret prompts. While it is capable of generating artworks and aiding in design and educational tools, it does not achieve perfect photorealism and may struggle with complex compositional tasks.