Gradio

@Gradio • 57,025 subscribers

Build and share machine learning apps in 3 lines of Python. Part of the @Huggingface family 🤗. DMs are open for sharing your gradio app with us for promotion!

Live Cam

Gradio

Shorts

😀 ToonCrafter: Generative Cartoon Interpolation 🔆 Can interpolate two cartoon images by leveraging the pre-trained image-to-video diffusion priors. Model on 🤗👇

Microsoft's OmniParser V2 just dropped. Now AI can : *understands every button* *identifies all interactive elements* *structures the entire GUI* Pure vision-based parsing. GUI automation just got a lot easier 🎯

🆕 Image super-resolution model just dropped! Superior results even with a single sampling step. 🔥InvSR: Arbitrary-steps Image Super-resolution via Diffusion Inversion.

Leffa from Meta is a 🆕 unified framework for controllable person image generation that enables precise manipulation of both appearance (i.e., Virtual try-on) and pose (i.e., Pose transfer). Learn more about 📚 Code,🔥 Demo, and 🤗 Model ⬇️

Trending: Step1X-3D for generating high-fidelity 3D assets with versatile textures! Apache-2.0 with exceptional results in terms of geometry and texture mapping🔥🔥

🔥Introducing VILA: The next-gen VLM for Video and inter-leaved image understanding with Apache-2.0 license! Is VILA the best in-class small VLM for edge-deployment? Keep reading🧵 👀

😍 🆕 DeepSeek Mixture-of-Experts VLMs are out on Hugging Face Spaces! Witness advanced multimodal understanding in the app linked. Available in 3 sizes: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small &amp; DeepSeek-VL2, with 1.0B, 2.8B &amp; 4.5B activated params resp. out of available 16B.

This simple HTML app has a drag-and-drop canvas, 20+ text effects, 3D extrusion, and perspective transforms for your 'text behind image'. 😎 Crazy part: The ML backend is ~50 lines of Python Built with gradio.Server ➡️ bring any frontend you want!

This is built using Gradio 6's super easy new HTML component! You can play with the demo here:

Switti -- a new scale-wise transformer for text-to-image generation 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.

Videos

Watch Anya Live

Object Cutter Create high-quality HD background removal for ANY object in your image with a text prompt or bounding boxes!

📚 ebook2audiobook CPU/GPU Converter from eBooks to audiobooks with chapters and metadata using Calibre, ffmpeg, XTTSv2, Fairseq and more. Supports voice cloning and 1100+ languages! 🤯 🗣️Voice cloning with your own voice 🖥️Designed to run on 4GB RAM ✅Runs on Colab 🤗On Spaces

KDTalker is really wild 🤯👇 - Can run on single 4090 or 3090 🤩 - Uses Diffusion for generating audio-driven Talking Portraits - Preserves character identity with fine facial details - Expressions change with the speech, giving high pose diversity

Meta has released Melody Flow!🚀 🎵 😮 High fidelity Music Generation for your prompt, and you can Edit your music too! [Sound: ON]

✨ Lights on, AI activated ✨ Upload ANY photo with lamp(s). Watch this app instantly illuminate it. No Photoshop. No editing skills needed. Just pure AI magic.🔥 Try Finegrain Light Switcher now.

Most "AI coding tools" need 5 files, a build config, and a prayer. Gradio 6's gr.HTML: one Python file. Frontend, backend, state—done 😎 Generate with Claude or any frontier LLM in one shot. Deploy in seconds. This is what vibe coding is supposed to be! Full breakdown👇️

⚡️ JUST DROPPED: Create custom AI voices in seconds! &gt; Mix multiple voices &gt; Zero coding needed &gt; Intuitive &amp; slick UI with voice sliders &gt; Built with Kokoro-82M; blazing fast! [🗣️ SOUND:ON]

This is amazing! You can now create high-quality 3D Scenes from a single image using Multi-Instance Diffusion Models (MIDI) 🔥

Text3D - a nice little gradio app that generates images that can be used to generate 3D artefacts downstream.

𝐒𝐔𝐏𝐈𝐑: An advanced image restoration method that combines generative prior and model scaling,using a 20-million image dataset, and can manipulate restorations with textual prompts. Kudos to Fanghua Yu Jinjin Gu Xintao Wang et al🚀 SUPIR supports Gradio demo in repo [links👇]

🆕 FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on

All this through a new Python library called daggr!🔥 Build AI workflows that can connect ML models, custom Python functions, and AI apps together🤯

VideoLLaMA3, latest MLLMs for image and video understanding. 🖐️ 7B models: DocVQA: 94.9, MathVision: 26.2, VideoMME: 66.2/70.3, MLVU: 73.0 🤏 2B models for edge devices: MMMU: 45.3, VideoMME: 59.6/63.4 👊 Frontier-class video model with ONLY 3M video-text pairs

MagicSketch 🤩 Interactive image editing Gradio app. 🤯 An MLLM even infers editing intent in real-time and generates a prompt for inpainting for you!

🆕 Our first launch in 2025! 🎊 We've added an agent to our Playground that can automatically capture any errors in the app, surface them, and rewrite the code to fix them!

Microsoft's OmniParser V2 just dropped. Now AI can : understands every button identifies all interactive elements structures the entire GUI Pure vision-based parsing. GUI automation just got a lot easier 🎯

😍 🆕 DeepSeek Mixture-of-Experts VLMs are out on Hugging Face Spaces! Witness advanced multimodal understanding in the app linked. Available in 3 sizes: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small & DeepSeek-VL2, with 1.0B, 2.8B & 4.5B activated params resp. out of available 16B.

⚡️ JUST DROPPED: Create custom AI voices in seconds! > Mix multiple voices > Zero coding needed > Intuitive & slick UI with voice sliders > Built with Kokoro-82M; blazing fast! [🗣️ SOUND:ON]