最新情報
Stability AI、初のオープンソースRLHF LLMチャットボット、StableVicuna をリリース
StableVicunaは、人間のフィードバックから強化学習（RLHF）により学習させた、初の大規模なオープンソースチャットボットです。StableVicunaは、Vicuna v0 13bをさらに細かく指示で微調整し、RLHFで学習させたバージョンで、細かく命令調整したものです。 LLaMA13bモデルです。興味のある読者のために、以下の内容を紹介します。
Stability AI、画像にテキストを組み込める強力なテキストトゥイメージモデル「DeepFloyd IF」をリリース
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.
Stability AI、画像アップスケーリングAPIをリリース
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.
Stability AI、言語モデルシリーズ「StableLM」の第1弾をリリース
Stability AI's open-source Alpha version of StableLM showcases the power of small, efficient models that can generate high-performing text and code locally on personal devices. Discover how StableLM can drive innovation and open up new economic opportunities while supporting transparency and accessibility in AI technology today.
Stability AI、アーティストPeter Gabrielとパートナーシップを組み、#DiffuseTogether と題したAIアニメーションチャレンジのシリーズを開始
Stability AI, together with music legend Peter Gabriel, announces the debut of its Stability AI DiffuseTogether Challenge. This groundbreaking initiative combines the power of generative AI imaging with the talents of a Rock & Roll Hall-of-Famer and is the first in a series of AI animation challenges that will feature other popular musicians from different genres.
Stability AI、Amazonの新サービスBedrock で Stable Diffusion モデルを利用可能に
Stability AI teams up with AWS to announce Amazon Bedrock, a new fully managed service that provides access to foundation models from Stability AI and other leading AI startups via an API. Join us in leveraging the power of AI to revolutionize your business today
Stable Diffusion XL ベータ版、APIカスタマーとDreamStudioユーザー向けにリリース
Stability AI's latest addition to the Stable Diffusion suite, SDXL, offers enterprise developers more detailed imagery and composition than its predecessor, Stable Diffusion 2.1. Discover how SDXL's advanced image generation capabilities can help take your business to the next level with Stability's APIs today.
Stability AIによるアニメーション技術が、Revel.xyzのAnimaiアプリケーションでデビュー
Stability AI, the world’s leading open source generative AI company, and Revel.xyz, the social collectibles platform, announced today the launch of Animai, a consumer animation tool powered by Stability AI’s animation technology.
Stable Diffusion Reimagine リリース
Stable Diffusion Reimagine is a new Clipdrop tool that allows users to generate multiple variations of a single image without limits. No need for complex prompts: Users can upload an image into the algorithm to create as many variations as they want.
Stability AIはClipdropの開発元であるInit MLを買収
Stability AI, the world’s leading open source generative AI company, announces that it has acquired Init ML, makers of the globally popular imaging tool Clipdrop.
Stability AI、3Dでテキストから画像まで作成できる Stability For Blender をリリース
Stability for Blender is a free, easy way to use Stable Diffusion inside Blender. Blender is a professional open-source 3D computer graphics software. This new tool allows users to generate textures, videos and more inside Stable Diffusion.
Stability AI、Krikey AIとパートナーシップを組み、AIアニメーションツールの提供を開始
Krikey.ai, an AI tools company, announced an AI Animation partnership with Stability AI today.
Stable Diffusion v2.1 と DreamStudio のアップデート
The latest release of Stable Diffusion, Version 2.1.
Stability AI Announces $101 Million in Funding for Open-Source Artificial Intelligence
Stability AI, the world's first community-driven, open-source artificial intelligence (AI) company, today announced USD $101 million in funding.
Stable Diffusion Public Release
We are delighted to announce the public release of Stable Diffusion and the launch of DreamStudio Lite.
Stable Diffusion Launch Announcement
The model itself builds upon the work of the team at CompVis and Runway in their widely used latent diffusion model combined with insights from the conditional diffusion models by our lead generative AI developer Katherine Crowson, Dall-E 2 by Open AI, Imagen by Google Brain and many others. We are delighted that AI media generation is a cooperative field and hope it can continue this way to bring the gift of creativity to all.