Our latest language model, Stable LM 3B, is a compact language model designed to operate on portable digital devices like handhelds and laptops.

Stability AI released its first Japanese vision-language model, Japanese InstructBLIP Alpha. It can generate textual descriptions for input images as well as generate answers to questions given images.

We are launching Stable Chat research preview, a new web interface that empowers the AI community to interactively evaluate our large language models. We are committed to promoting transparency in AI, and our participation in DEF CON deepens our collaboration with external security researchers.

Stability AI released its first Japanese language model, Japanese StableLM Alpha (JPLM), the best-performing openly available LM created for Japanese speakers.

Stability AI has just announced the release of StableCode, its very first LLM generative AI product for coding. This product is designed to assist programmers with their daily work while also providing a great learning tool for new developers ready to take their skills to the next level.

The Stability AI team is proud to release as an open model SDXL 1.0, the next iteration in the evolution of text-to-image generation models. Following the limited, research-only release of SDXL 0.9, the full version of SDXL has been improved to be the world's best open image generation model.

Stability AI and its CarperAI lab proudly announce Stable Beluga 1 and its successor Stable Beluga 2 (formerly codenamed FreeWilly), two powerful new, open access, Large Language Models (LLMs). Both models demonstrate exceptional reasoning ability across varied benchmarks.

Explore the New Stability AI Developer Platform, designed to streamline API discovery and integration. Our blog post unveils key features like the Sandbox Playground, Uniform Documentation, Simplified API Key Management, and Improved Navigation. Empower developers to unleash the full potential of our APIs.

Discover SDXL 0.9, Stability AI's cutting-edge release in the Stable Diffusion suite. Unleashing remarkable image and composition precision, this upgrade revolutionizes generative AI imagery. From hyper-realistic media production to design and industrial advancements, explore the limitless possibilities of SDXL's practical applications.

Unleash your creativity with Reimagine XL by Clipdrop! Upgrade to the ultimate image reimagination tool, exclusively on Clipdrop. Remove pixel sourcing, and get bold and unique results. High-quality output handles various aspect ratios. No technical know-how is needed. Redecorate, create, transform. Explore now!

Stability AI introduces StableStudio, the open-source version of DreamStudio, its premier text-to-image consumer application. This release marks a new era in the company's imaging pipeline and emphasizes its commitment to advancing open-source development within the AI ecosystem.

Stability AI has released Stable Animation SDK, a powerful tool that allows artists and developers to create stunning animations using advanced Stable Diffusion models. With the ability to create animations from prompts, source images, or source videos, users can fully utilize all the Stable Diffusion models, including Stable Diffusion 2.0 and Stable Diffusion XL.

We are proud to present StableVicuna, the first large-scale open source chatbot trained via reinforced learning from human feedback (RHLF). StableVicuna is a further instruction fine-tuned and RLHF-trained version of Vicuna 13b, an instruction fine-tuned LLaMA 13b model.

DeepFloyd IF is a state-of-the-art text-to-image model released on a non-commercial, research-permissible license that allows research labs to examine and experiment with advanced text-to-image generation approaches. In line with other Stability AI models, Stability AI intends to release a DeepFloyd IF model fully open source at a future date.

The Image Upscaling API is the latest addition to Stability AI’s existing image generation and editing APIs, like the popular text-to-image, image-to-image and inpainting APIs. Upscaling adds to those popular tools by expanding small images into larger ones while maintaining – or even improving – their level of detail.