Build and share machine learning apps in 3 lines of Python. Part of the @Huggingface family ๐ค.
DMs are open for sharing your gradio app with us!
Jan 27 โข 5 tweets โข 2 min read
๐ฅWILD! @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... ๐งต
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! ๐ฏ
@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! ๐
Dec 9, 2024 โข 4 tweets โข 2 min read
๐ SwiftEdit: Lightning Fast Text-guided Image Editing via One-step Diffusion
Make your edit in just 0.23 seconds !!! ๐คฏ
User-friendly, lightning-fast editing gradio-app that enables instant edits through simple prompts, delivering precise results.๐ Learn more about the project
SwiftEdit
> You can edit facial Identity and expressions via flexible text prompts
Oct 9, 2024 โข 7 tweets โข 3 min read
Welcome, Gradio 5 ๐
Weโve 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 weโve 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!)
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! ๐๏ธ๐จ
Jul 15, 2024 โข 4 tweets โข 2 min read
๐ฅ ๐ฅ 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 ๐ค
๐ Generate 3D characters with CharacterGen (SIGGRAPH'24)
๐Introducing 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-Interleave๐ฅ
- Interleave data format unifies different tasks.
- New datasets on ๐คHub:
1๏ธโฃM4-Instruct, high-quality dataset, 1.1M samples from domains: multi-image, video, 3D & single-image
2๏ธโฃLLaVA-Interleave Bench - Set of tasks to evaluate multi-image capabilities
Jul 9, 2024 โข 6 tweets โข 3 min read
๐ฅIntroducing 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 reading๐งต ๐
VILA uses interleaved image-text pretraining and it unlocks cool capabilities:
- Video & multi-image understanding ๐ฌ
- In-context learning ๐ง , and
- Visual chain-of-thought ๐ก
Experience the future -- Edge deployment ๐ฑof VLMs! Try the demo now! ๐
Jun 12, 2024 โข 4 tweets โข 2 min read
๐คฏ MimicBrush might be the coolest AI app on ๐ค Spaces right now!
In-the-wild results are really something!๐
๐จMimicBrush: New way to edit images with reference imitation! ๐ผ๏ธ๐
- Zero-shot editing๐ฏ
- Use in-the-wild references for inspiration๐คฉ
- Learns semantic correspondence through self-supervised learning ๐ง
- Outperforms existing alternatives in various test cases ๐
- Demo๐
Jun 12, 2024 โข 4 tweets โข 1 min read
๐ฅ SD3 has finally arrived on Huggingface!
Learn everything you'd need to get started๐
๐SD3-Medium: A very powerful t2i model
๐Exciting news for the open-source world of AI! Google has released ๐๐๐ฅ๐ข๐๐๐ฆ๐ฆ๐, a family of vision-language models (pre-trained & fine-tuned)
๐PaliGemma can take an image and text as input and generate bounding boxes, segmentation masks, do visual Q&A, and much more๐ธ
๐ช PaliGemma has 3 flavors: Pretrained (pt), Mix, and Fine-tuned (ft) models, each with different resolutions and precisions.
๐งฉ All models are available on the @huggingface Hub with nice model cards and with ๐ฅ ๐๐ซ๐๐ง๐ฌ๐๐จ๐ซ๐ฆ๐๐ซ๐ฌ ๐ข๐ง๐ญ๐๐ ๐ซ๐๐ญ๐ข๐จ๐ง ๐ค
May 14, 2024 โข 6 tweets โข 5 min read
๐คฉ Gradio project has been trending on Github, ๐ฅ alongside TEN GenAI projects that are leveraging Gradio for their development!!
Projects are from across the board, more in ๐งต๐:
โ Voice generation
โ Video editing
โ Image generation
โ Cool LLMs
โ Multimodal
โ Audio generation
โ Applio - VITS-based Voice Conversion focused on simplicity, quality & performance
๐
Congratulations to AUTOMATIC1111: A Stable Diffusion Web-UI built using @Gradio for 100k @github stars! ๐๐ฅณ
๐ผ๏ธAutomatic1111 is the Ultimate Creative Playground!๐
Let's explore in this thread what all is possible with this feature-packed Web UI ๐๐งต
1๏ธโฃ One-click install & run script for easy setup๐ฅ
2๏ธโฃ Outpainting, inpainting, color sketching โ unleash your artistic vision๐จ
3๏ธโฃ Control attention with ((image-element)) format for focus๐๏ธ
4๏ธโฃ Loopback & X/Y/Z plots for dynamic image transformations๐
5๏ธโฃ Generate variations๐
Jul 17, 2023 โข 7 tweets โข 3 min read
BIG NEWS ๐ฅณ๐
Building Chatbots apps just got wayyy easier: announcing the new ๐ฒ๐๐๐๐ธ๐๐๐๐๐๐๐๐ class ๐
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...
The ๐ฒ๐๐๐๐ธ๐๐๐๐๐๐๐๐ 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!)
Apr 13, 2023 โข 6 tweets โข 2 min read
๐ซ We're excited to launch a NEW Python library ๐ซ
The ๐๐๐๐๐๐_๐๐๐๐๐๐ library lets you run any Gradio app as an API ๐
See a cool Hugging Face Space? Use it programmatically instantly:
You can connect to private Spaces by passing in your Hugging Face token
Oct 27, 2022 โข 6 tweets โข 2 min read
Gradio 3.7 is out! Everything that is new in 3.7 ๐ฝ
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! 2. A new upload() event for Video, Audio, Image, and File components:
Sep 8, 2022 โข 4 tweets โข 2 min read
Excited to release 3 big features as part of ๐๐๐๐๐๐ ๐น.๐น ๐งก
1. Iterative outputs: you can now `yield` a sequence of outputs and they will show up sequentially in your Gradio demo:
2. The ๐๐๐๐๐๐.๐ฐ๐๐๐๐๐๐๐๐ class, which allows you to toggle on/off the visibility of components (think advanced options) in your demo very easily:
Jun 2, 2022 โข 7 tweets โข 5 min read
Now it's time for our favorite part of the Blocks Party: awarding the top machine learning demos ๐
We had more than 50 incredibly creative and complex demos, built entirely in Python๐ซ
Here are the top 5, as voted by your likes... ๐งก
In 5th place, with 22 likes, is: StyleGAN-NADA ๐ฅณ
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!