Gradio

Freepik's Flux.1-lite-8B-alpha is making a lot of noise and is trending on Hugging Face rn. > Alpha release of Flux.1 Lite > 8B transformer model distilled from the FLUX.1-dev > Uses <7 GB RAM and runs 23% faster > Try with FREE Gradio app: https://lnkd.in/gRUEE7hB

I added full Gradio 5 support to this multimodal chat (version 5.1.0 tested) in addition to other enhancements, such as audio conversation rendering in the chat and sympy support in the Python code interpreter (running in a Lambda function). It can run 100% locally including OpenSearch for the vector text and multimodal indexes. Let me know what you think!

Gradio 5 is here! And you can now easily connect your Gradio app to a scalable inference backend powered by BentoML. In BentoML 1.3.8, we introduced a new API to simplify how to integrate Gradio for adding Web UIs to your AI service backend built with BentoML 🍱 For BentoML users: • Build a slick web UI for your custom models in Python! • Check out the amazing playground gradio.app/playground by the Hugging Face team to get started! • No need to manage Gradio app separately from your BentoML deployments For Gradio users: • Supercharge your Gradio app with efficient LLM serving, multi-model pipelines and inference tasks dispatching with global queue and distributed workers • Dynamic batching of incoming inference requests to improve GPU utilization and reduce latency • Simplified production deployment with auto-generate docker container images and built-in performance metrics • Speed up model loading, auto-scaling and cold-start when deployed via BentoCloud ☁️ 👩💻 BentoML & Gradio integration demo: https://lnkd.in/gnZKpMN5

📣 Introducing Framer: Create video by interpolating between 2 frame images🔥 A new AI model that produces smooth transitioning videos between two images. Allows customizing the trajectory of selected key points as well (as shown in the attached video of their gradio app) Code and Gradio app are coming soon on Hugging Face Spaces. Stay tuned! Project: https://lnkd.in/g4_Y45Dr

📣 Introducing Framer: Create video by interpolating between 2 frame images🔥 A new AI model that produces smooth transitioning videos between two images. Allows customizing the trajectory of selected key points as well (as shown in the attached video of their gradio app) Code and Gradio app are coming soon on Hugging Face Spaces. Stay tuned! Project: https://lnkd.in/g4_Y45Dr

Meta has released Melody Flow!🚀 🎵 😮 High fidelity Music Generation and editing using text prompt! [Sound: ON] Model is based on a diffusion transformer architecture trained on a flow-matching objective the model can Generate and Edit diverse high quality stereo samples of variable duration, with simple text descriptions. The official Gradio app is up on Hugging Face Spaces: https://lnkd.in/gRJ52YB9 Model on Hugging Face hub: https://lnkd.in/gJ6AuArS

Aya Expanse models from Cohere For AI can chat, listen, speak, and generate image in 23 world languages🔥🤯 Key highlights: > Super slick official Gradio 5 app: https://lnkd.in/gpdREf7t > Can chat, speak and generate Images > Multilingual model -- Understands 23 languages > Models released on Hugging Face Hub: aya-expanse-32B and aya-expanse-8B > Developed by: Cohere For AI and Cohere > Highly advanced capabilities and great benchmark performances. Refer blog: https://lnkd.in/gUtQbJa3 > Connect the world across languages and various GenAI domains > License: CC-BY-NC, also requires adhering to C4AI's Acceptable Use Policy

OmniParser 🤩 Microsoft has casually dropped this gem to enable GPT4V to navigate your computer! Looks like, 'Computer use' is the next battleground. More details👇 > Screen Parsing tool for Pure Vision Based GUI Agent > A method for parsing user interface screenshots into structured and easy-to-understand elements. > This significantly enhances the ability of OpenAI's GPT-4V to generate actions 🤯 > Makes it possible for powerful LLMS to accurately ground the corresponding regions of interest in an interface. > 🚀 Understanding the user interfaces like never before! 🤗 Model on Hugging Face with MIT license: https://lnkd.in/gxT-hBvz 👉 Launch the local Gradio app by following the instructions here: https://lnkd.in/gzVh8ppb

It's here already!! Anthropic's Computer Use - out-of-the-box, no docker required! 🤯 🔥 Supports any platform, starting with Windows. Launches a user-friendly interface based on Gradio🌟 More details: 👇 > Project name: Computer Use - OOTB > An out-of-the-box (OOTB) solution for Claude's new Computer Use APIs. No Docker deployment is required. It theoretically supports any platform, with testing currently done on Windows. > 🤩 Extremely easy to launch: Clone the repo, install from requirements, and launch the app `python app_py` > A user-friendly interface based on Gradio will launch locally 🎨 > 👉 Repo for Computer_Use_OOTB: https://lnkd.in/gMjWVyym

Great news for users of Anthropic's "Computer Use"! Gradio has released safehttpx, a small Python library to help developers protect their applications from Server Side Request Forgery (SSRF) attacks. With LLMs now able to control computers, safety has never been this important. Attackers can potentially access sensitive internal services that are normally unreachable from the internet. Keeping this in mind, Gradio has released safehttpx with Trail of Bits: > Integrated in Gradio 5 too! > 𝚜𝚊𝚏𝚎𝚑𝚝𝚝𝚙𝚡 is a standalone repo that you can use in your own web framework for securely making GET requests. > This is the first Python library that lets you make asynchronous GET requests safely. Enjoy! Access the new library here: https://lnkd.in/g7Z-kt3S