Stability AI Unveils Advanced Text-to-Image Model Stable Diffusion XL 1.0

min read



Stability AI Unveils Advanced Text-to-Image Model Stable Diffusion XL 1.0

Leading open, generative AI company Stability AI has announced the launch of Stable Diffusion XL (SDXL) 1.0, the most advanced version of its text-to-image model suite. SDXL 1.0 will be featured on Amazon Bedrock, a fully managed service by Amazon Web Services Inc. (AWS), which offers foundation models from prominent AI startups.

The unveiling at the annual AWS Summit New York highlights Amazon’s commitment to delivering powerful text-to-image foundation models to its customers. It also signifies Stability AI’s commitment to collaborate with AWS to provide superior solutions for developers and clients.

The model is available through Stability AI API, Github page, Clipdrop, and DreamStudio consumer applications. It will also be hosted on Amazon SageMaker JumpStart, a machine learning (ML) hub that offers ML algorithms, models, and solutions.

The SDXL 1.0 release follows the research-only SDXL 0.9 version launched in June, which was refined using use-case testing data. This process has resulted in a model that produces more vibrant, accurate colors with improved contrast, lighting, and shadows. It also generates 1-megapixel resolution images quicker and in various aspect ratios.

Stability AI’s new fine-tuning feature allows users to specialize image generation using just a few images. The SDXL 1.0 model, with its large parameter counts, promises better color accuracy and finer details.

Since the beta launch, ClipDrop users have already generated over 35 million images using the model, while the Stability AI Discord community generates an average of 20,000 images daily.

The launch expands the selection of Amazon Bedrock with the addition of Stability AI’s SDXL 1.0 model, enabling customers to build and scale generative AI applications. This follows the company’s series of developments, including the recent launch of Stable Doodle, a sketch-to-image tool that generated over 3 million images within a week of its release.

Make sure to join our AI Tools Info Facebook Page, Instagram, and Pinterest for exciting updates on AI innovations and inspiring projects. If you have any inquiries about the content presented above or if there’s anything we might have overlooked, don’t hesitate to reach out to us at