Computers have long been great at complex tasks like analysing data, but not so great at simple tasks like recognizing & moving objects. With RT-2, we’re bridging that gap by helping robots interpret & interact with the world and be more useful to people.
MULTIMODAL AI
-
SDXL Model Performance Across Different Image Resolutions
By
–
See how SDXL handles all the resolutions pic.twitter.com/TCCx5QGKmc
— Replicate (@replicate) 28 juillet 2023See how SDXL handles all the resolutions
-
Gen-2 Image to Video: Moments of Tranquility
By
–
A few moments of tranquility with Gen-2 Image to Video. pic.twitter.com/DMmJltQ7Ld
— Runway (@runwayml) 28 juillet 2023A few moments of tranquility with Gen-2 Image to Video.
-
Visual Foundation Models: Architectures, Training, and Prompting Survey
By
–
Foundational Models Defining a New Era in Vision: A Survey and Outlook A comprehensive survey of visual foundation models. Covers emerging architectures(for vision+other modalities), training objectives, pre-training datasets, fine-tuning mechanisms, and the common prompting
-
SDXL Model Guide: Image Generation, Inpainting, and Refinement Techniques
By
–
This guide covers the basics, but also shows how you can use the SDXL model to: • make an image from another image (img2img)
• inpaint using a mask
• use a refiner to add fine-detail to your images -
Google Research Neural Networks Learn Physical World Objects ICML2023
By
–
Today at 10:30 AM, drop by the #ICML2023 Google Research booth, where @tkipf will demonstrate how we created neural networks that can learn objects in the physical world, enabling us to train structured scene understanding models with less supervision.
-
Stability AI launches Stable Diffusion XL 1.0 on Amazon Bedrock
By
–
Stability AI unveils Stable Diffusion XL 1.0, now available on Amazon Bedrock for developers worldwide #StabilityAI #AI #AIcommunity #TextToImage #OpenSource #AWS #SDXLhttps://t.co/QC1mxb3dtk pic.twitter.com/2FAQAoKjLS
— Stability AI (@StabilityAI) 26 juillet 2023Stability AI unveils Stable Diffusion XL 1.0, now available on Amazon Bedrock for developers worldwide #StabilityAI #AI #AIcommunity #TextToImage #OpenSource #AWS #SDXL https://
bit.ly/3O7N3Ch -
New Image to Video Mode Generates Stunning Greenery Sequences
By
–
Generated greenery. Made with the new Image to Video mode in Gen-2. pic.twitter.com/Souui3kk87
— Runway (@runwayml) 26 juillet 2023Generated greenery. Made with the new Image to mode in Gen-2.
-
Generative AI transforms audiovisual content creation tools
By
–
La ia generativa está cambiando el mundo. A medida que estos sistemas avanzan y mejoran los resultados que obtenemos, se está abriendo un nuevo mundo de posibilidades para la creación de contenido audiovisual.
— Juan Merodio (@juanmerodio) 26 juillet 2023
En el vídeo vemos cómo dos herramientas trabajan juntas; una de… pic.twitter.com/kpttgnMRf6La ia generativa está cambiando el mundo. A medida que estos sistemas avanzan y mejoran los resultados que obtenemos, se está abriendo un nuevo mundo de posibilidades para la creación de contenido audiovisual. En el vídeo vemos cómo dos herramientas trabajan juntas; una de
-
Wav2Lip and ElevenLabs Create Believable AI-Generated Videos
By
–
wav2lip + eleven and you have believable videos https://t.co/TQrsolSVA3
— Varun Mayya (@waitin4agi_) 26 juillet 2023wav2lip + eleven and you have believable videos