Gradio Profile picture
Build and share machine learning apps in 3 lines of Python. Part of the @Huggingface family ๐Ÿค—. DMs are open for sharing your gradio app with us!
Jan 27 โ€ข 5 tweets โ€ข 2 min read
๐Ÿ”ฅWILD! @AnthropicAI released Citations API for Claude last week -- a game-changing feature that will allow you to build trustworthy AI systems. Here's why this is HUGE... ๐Ÿงต

1/ Build reliable RAG systems. AI should prove its work, not just give "trust me bro" responses. Anthropic's Citations API solves this elegantly: feed docs to Claude, enable citations, and get perfect source references! ๐ŸŽฏ @AnthropicAI 2/ What makes Citations special:

- Zero prompt engineering needed
- Automatic text chunking
- Works with PDFs & plain text
- Precise page/character citations
- Super efficient token usage
- Built for streaming
- No more complex citation systems! ๐Ÿš€
Dec 9, 2024 โ€ข 4 tweets โ€ข 2 min read
๐Ÿ†• SwiftEdit: Lightning Fast Text-guided Image Editing via One-step Diffusion

Make your edit in just 0.23 seconds !!! ๐Ÿคฏ

User-friendly, lightning-fast editing gradio-app that enables instant edits through simple prompts, delivering precise results.๐Ÿ‘‡ Learn more about the project SwiftEdit
> You can edit facial Identity and expressions via flexible text prompts Image
Oct 9, 2024 โ€ข 7 tweets โ€ข 3 min read
Welcome, Gradio 5 ๐Ÿ‘‹

Weโ€™ve been hard at work over the past few months, and we are excited to announce today the stable release of Gradio 5!

With more than 2 million users every month (and >470,000 apps on Hugging Face Spaces), Gradio has become the default way to build, share, and use machine learning applications.

Our goal with Gradio 5 was to address the most common pain points that weโ€™ve heard from Gradio developers about taking these apps to production. Here are 5 new things in Gradio 5 (including a new way to build Gradio apps without writing any code!)Image Does Gradio load too slowly for you?

Well, not anymore! Gradio 5 ships with major performance improvements, including the ability to serve apps via server-side rendering (SSR) which loads Gradio apps almost instantaneously in the browser. No more loading spinner! ๐ŸŽ๏ธ๐Ÿ’จ
Jul 15, 2024 โ€ข 4 tweets โ€ข 2 min read
๐Ÿ”ฅ ๐Ÿ”ฅ Generate 3D characters with CharacterGen (SIGGRAPH'24)

- Generated 3D characters have high-quality shapes and textures
- Useful for downstream applications such as animation and game dev
- Code, demo, and pretrained weights available now on ๐Ÿค— ๐Ÿš€ Generate 3D characters with CharacterGen (SIGGRAPH'24)

๐Ÿ‘‰ Official Demo on @huggingface Spaces: huggingface.co/spaces/VAST-AIโ€ฆ
Jul 11, 2024 โ€ข 4 tweets โ€ข 2 min read
๐Ÿš€Introducing LLaVA-NeXT Interleave: Now AI can understand and reason with multiple images at once

- This opens up multi-image scenarios like multi-frame videos, multi-view 3D, and multiple inter-leaved images.
- An all round LMM that can understand videos, images, and 3D
Moreโฌ‡๏ธ LLaVA-NeXT-Interleave๐Ÿ”ฅ
- Interleave data format unifies different tasks.
- New datasets on ๐Ÿค—Hub:
1๏ธโƒฃM4-Instruct, high-quality dataset, 1.1M samples from domains: multi-image, video, 3D & single-image
2๏ธโƒฃLLaVA-Interleave Bench - Set of tasks to evaluate multi-image capabilities
Jul 9, 2024 โ€ข 6 tweets โ€ข 3 min read
๐Ÿ”ฅIntroducing 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 reading๐Ÿงต ๐Ÿ‘€ VILA uses interleaved image-text pretraining and it unlocks cool capabilities:

- Video & multi-image understanding ๐ŸŽฌ
- In-context learning ๐Ÿง , and
- Visual chain-of-thought ๐Ÿ’ก

Experience the future -- Edge deployment ๐Ÿ“ฑof VLMs! Try the demo now! ๐Ÿ‘‡ Image
Jun 12, 2024 โ€ข 4 tweets โ€ข 2 min read
๐Ÿคฏ MimicBrush might be the coolest AI app on ๐Ÿค— Spaces right now!

In-the-wild results are really something!๐Ÿš€ ๐ŸŽจMimicBrush: New way to edit images with reference imitation! ๐Ÿ–ผ๏ธ๐Ÿ”

- Zero-shot editing๐ŸŽฏ
- Use in-the-wild references for inspiration๐Ÿคฉ
- Learns semantic correspondence through self-supervised learning ๐Ÿง 
- Outperforms existing alternatives in various test cases ๐Ÿ“ˆ
- Demo๐Ÿ‘‡ Image
Jun 12, 2024 โ€ข 4 tweets โ€ข 1 min read
๐Ÿ”ฅ SD3 has finally arrived on Huggingface!

Learn everything you'd need to get started๐Ÿ‘‡ Image ๐ŸŒŸSD3-Medium: A very powerful t2i model

- Multimodal Diffusion Transformer (MMDiT) architecture๐Ÿง 
- Trained on 1B images, 30M aesthetic & 3M preference data๐Ÿคฏ
- Improved image quality, typography & prompt understanding๐Ÿ’ก
- Non-commercial allowed, commercial license required๐Ÿ“œ
May 15, 2024 โ€ข 4 tweets โ€ข 2 min read
๐ŸŽ‰Exciting news for the open-source world of AI! Google has released ๐๐š๐ฅ๐ข๐†๐ž๐ฆ๐ฆ๐š, a family of vision-language models (pre-trained & fine-tuned)

๐ŸŒŸPaliGemma can take an image and text as input and generate bounding boxes, segmentation masks, do visual Q&A, and much more๐Ÿ“ธ ๐Ÿ’ช PaliGemma has 3 flavors: Pretrained (pt), Mix, and Fine-tuned (ft) models, each with different resolutions and precisions.
๐Ÿงฉ All models are available on the @huggingface Hub with nice model cards and with ๐Ÿ”ฅ ๐“๐ซ๐š๐ง๐ฌ๐Ÿ๐จ๐ซ๐ฆ๐ž๐ซ๐ฌ ๐ข๐ง๐ญ๐ž๐ ๐ซ๐š๐ญ๐ข๐จ๐ง ๐Ÿค— Image
May 14, 2024 โ€ข 6 tweets โ€ข 5 min read
๐Ÿคฉ Gradio project has been trending on Github, ๐Ÿ”ฅ alongside TEN GenAI projects that are leveraging Gradio for their development!!

Projects are from across the board, more in ๐Ÿงต๐Ÿ‘‡:
โœ…Voice generation
โœ…Video editing
โœ…Image generation
โœ…Cool LLMs
โœ…Multimodal
โœ…Audio generation Image โœ… Applio - VITS-based Voice Conversion focused on simplicity, quality & performance
๐Ÿ”—

โœ… FunClip - Open source, accurate and convenient video slicing tool
๐Ÿ”— github.com/IAHispano/Applโ€ฆ
github.com/alibaba-damo-aโ€ฆ
Image
Sep 4, 2023 โ€ข 7 tweets โ€ข 4 min read
Congratulations to AUTOMATIC1111: A Stable Diffusion Web-UI built using @Gradio for 100k @github stars! ๐ŸŽ‰๐Ÿฅณ

๐Ÿ–ผ๏ธAutomatic1111 is the Ultimate Creative Playground!๐Ÿš€

Let's explore in this thread what all is possible with this feature-packed Web UI ๐Ÿ‘‡๐Ÿงต Image 1๏ธโƒฃ One-click install & run script for easy setup๐Ÿ“ฅ
2๏ธโƒฃ Outpainting, inpainting, color sketching โ€“ unleash your artistic vision๐ŸŽจ
3๏ธโƒฃ Control attention with ((image-element)) format for focus๐Ÿ‘๏ธ
4๏ธโƒฃ Loopback & X/Y/Z plots for dynamic image transformations๐Ÿ“Š
5๏ธโƒฃ Generate variations๐Ÿ”„ Image
Jul 17, 2023 โ€ข 7 tweets โ€ข 3 min read
BIG NEWS ๐Ÿฅณ๐ŸŽˆ

Building Chatbots apps just got wayyy easier: announcing the new ๐™ฒ๐š‘๐šŠ๐š๐™ธ๐š—๐š๐šŽ๐š›๐š๐šŠ๐šŒ๐šŽ class ๐Ÿ™Œ

The *fastest* way to build to build a Chatbot UI in Python -- including streaming, undo/retry, API, all out of the box!

Let's take a look at a few examples... Image The ๐™ฒ๐š‘๐šŠ๐š๐™ธ๐š—๐š๐šŽ๐š›๐š๐šŠ๐šŒ๐šŽ only has 1 required parameter: a function that takes in:

- an input message (string)
- a history (list of list of strings)

and returns:
- a response (string)

Here's a toy example: (for the example above!) Image
Apr 13, 2023 โ€ข 6 tweets โ€ข 2 min read
๐Ÿ’ซ We're excited to launch a NEW Python library ๐Ÿ’ซ

The ๐š๐š›๐šŠ๐š๐š’๐š˜_๐šŒ๐š•๐š’๐šŽ๐š—๐š library lets you run any Gradio app as an API ๐Ÿš€

See a cool Hugging Face Space? Use it programmatically instantly: Image You can connect to private Spaces by passing in your Hugging Face token Image
Oct 27, 2022 โ€ข 6 tweets โ€ข 2 min read
Gradio 3.7 is out! Everything that is new in 3.7 ๐Ÿ”ฝ

1. Gradio now supports *batched* function. You can specify a batch size and Gradio will automatically batch incoming requests so that your demo runs on a lot faster on Spaces! Image 2. A new upload() event for Video, Audio, Image, and File components: Image
Sep 8, 2022 โ€ข 4 tweets โ€ข 2 min read
Excited to release 3 big features as part of ๐š๐š›๐šŠ๐š๐š’๐š˜ ๐Ÿน.๐Ÿน ๐Ÿงก

1. Iterative outputs: you can now `yield` a sequence of outputs and they will show up sequentially in your Gradio demo: 2. The ๐š๐š›๐šŠ๐š๐š’๐š˜.๐™ฐ๐šŒ๐šŒ๐š˜๐š›๐š๐š’๐š˜๐š— class, which allows you to toggle on/off the visibility of components (think advanced options) in your demo very easily:
Jun 2, 2022 โ€ข 7 tweets โ€ข 5 min read
Now it's time for our favorite part of the Blocks Party: awarding the top machine learning demos ๐Ÿ†

We had more than 50 incredibly creative and complex demos, built entirely in Python๐Ÿ’ซ

Here are the top 5, as voted by your likes... ๐Ÿงก In 5th place, with 22 likes, is: StyleGAN-NADA ๐Ÿฅณ

Built by @RinonGalt, he demo allows you to edit specific attributes in your face, and generate a new picture with specific styles turned on or off. It's scary good!

Link: huggingface.co/spaces/Gradio-โ€ฆ