Stability is open-sourcing Stable Video Diffusion and an image-to-video model, for research purposes.
The 3D files that are generated can be exported in standard .obj format and refined in 3D software like Blender and Maya, or imported in a game engine, such as Unreal Engine 5 or Unity.
Early audio samples demonstrate Stable Audio's potential for creating diverse musical compositions tailored to user prompts.
During testing, the model successfully provided detailed Japanese descriptions of various input images. It also answered basic questions about the content of images, like identifying the number of people or objects.
The new website provides an opportunity for the open source AI community to directly evaluate and assist in strengthening these state-of-the-art models.
The new 7 billion parameter general-purpose language model aims to provide Japanese users with enhanced AI capabilities for text generation.
New research from Berkely present an approach that, given any video in the wild, can jointly reconstruct the underlying humans in 3D, and track them over time.
Stability AI has announced StableCode, it’s very first LLM generative AI product for coding. StableCode provides AI-assisted coding capabilities that aim to boost programmer productivity and lower barriers to entry for aspiring developers. While conversational AI assistants like Llama, ChatGPT, and Bard are already capable of writing code, they
Compared to other image generation models, SDXL achieves superior photorealism, artistic style replication across genres, and handling of difficult concepts like hands and text.
Using innovative synthetic data generation techniques, Stability AI researchers trained both models to reach state-of-the-art performance on reasoning and language tasks.
Open-source AI chatbots are rapidly advancing, and Stability AI's latest project, StableVicuna, showcases the power of innovative learning techniques in driving this progress.
DeepFloyd IF is a new state-of-the-art text-to-image model from Stability AI. The model boasts advanced features, including deep text understanding and high photorealism.
The new Image Upscaling API focuses on preserving quality and enhancing details in upscaled images.
The San Francisco startup aims to revolutionize the AI landscape with its transparent, accessible, and supportive language models.