SDXL 1.0 is Finally Here!

CyberSteampunkNightCafe artwork with SDXL 1.0
CyberSteampunkNightCafe artwork of SDXL 1.0 created with NightCafe Studio (courtesy: Author)

It’s here!

SDXL 1.0 is now officially released to the public after months of testing and fine-tuning by internal StabilityAI staff and external users.

Here is the announcement from StabilityAI:

SDXL 1.0 has one of the largest parameter counts of any open access image model, built on an innovative new architecture composed of a 3.5B parameter base model and a 6.6B parameter refiner.

The full model consists of a mixture-of-experts pipeline for latent diffusion: In the first step, the base model generates (noisy) latents, which are then further processed with a refinement model specialized for the final denoising steps. Note that the base model can also be used as a standalone module.

This two-stage architecture allows for robustness in image generation without compromising on speed or requiring excess compute resources. SDXL 1.0 should work effectively on consumer GPUs with 8GB VRAM or readily available cloud instances.

You can try SDXL 1.0 for yourself with ClipDrop, DreamStudio, NightCafe Studio, or by using API.

NightCafe Studio is currently reserving SDXL 1.0 for PRO users, but you can create 10 artworks as a FREE user.

Leave a Reply

Your email address will not be published. Required fields are marked *