Stable LM 2 12B is a pair of powerful 12 billion parameter language models trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch, featuring a base and instruction-tuned model. You can now try the model here:
@stabilityai
-
US Government Consults on Open Foundation Models Regulation
By
–
The U.S. Government is conducting a public consultation on the potential benefits, risks, and regulation of open foundation models. We’re pleased to share our response to this inquiry, prepared by our Head of Public Policy @opensauceai
, here: https://
bit.ly/3U5f3L5 Key -
Stable Audio 2.0 trained on licensed music with creator compensation
By
–
@stableaudio 2.0 was exclusively trained on a licensed dataset from the @AudioSparx music library, honoring opt-out requests and ensuring fair compensation for creators. (3/3)
-
Stable Audio 2.0 Generates Full Coherent Music Tracks
By
–
Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt.
— Stability AI (@StabilityAI) 3 avril 2024
Explore the model and start creating for free at: https://t.co/E9ZIGagmPf
Read the… pic.twitter.com/rFGb0KpdeXIntroducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt. Explore the model and start creating for free at: http://
stableaudio.com Read the -
Stable Audio 2.0 Transforms Audio with Natural Language Prompts
By
–
@stableaudio 2.0 goes beyond text-to-audio to include audio-to-audio capabilities. Users can now upload audio samples and, through natural language prompts, transform these samples into a wide array of sounds. (2/3) pic.twitter.com/VFJerw9pWJ
— Stability AI (@StabilityAI) 3 avril 2024@stableaudio 2.0 goes beyond text-to-audio to include audio-to-audio capabilities. Users can now upload audio samples and, through natural language prompts, transform these samples into a wide array of sounds. (2/3)
-
Stable Code Instruct 3B: New Instruction-Tuned LLM Released
By
–
Introducing Stable Code Instruct 3B, our new instruction tuned LLM based on Stable Code 3B. With natural language prompting, this model can handle a variety of tasks such as code generation, math and other software engineering related outputs.
— Stability AI (@StabilityAI) 25 mars 2024
This model’s performance rivals… pic.twitter.com/RsZhKpWu57Introducing Stable Code Instruct 3B, our new instruction tuned LLM based on Stable Code 3B. With natural language prompting, this model can handle a variety of tasks such as code generation, math and other software engineering related outputs. This model’s performance rivals
-
Stability AI Announces Major Update or Product Release
By
–
An announcement from Stability AI: https://
bit.ly/43zsVjN -
Natural language image and video editing with inpainting and outpainting
By
–
Edit: Intuitively edit images and videos through natural language prompts, encompassing tasks such as inpainting, outpainting, and modification. (4/4)
-
Advanced AI Image Upscaler Enhances Resolution to 4K
By
–
Upscale: Upscale images to 4k by utilizing our advanced creative upscaler services to enhance the resolution and quality of images and videos without compromising detail. (3/4)
-
Stable Image Core and Diffusion 3 image generation launch
By
–
Generate: Create new, original media from text descriptions using our flagship image service Stable Image Core or our groundbreaking image models including the soon to be released Stable Diffusion 3. (2/4)