Gradio

📣 New Text to Video research released: VADER - Adapts large-scale T2V models to specific downstream tasks - Uses pre-trained reward models, instead of supervised ft - The approach enables: Aesthetic video generation, Better alignment between text & videos, 3 times longer videos than training lengths🤯 ✨ VADER or Video Diffusion Alignment via Reward Gradients Model on @huggingface Hub: https://lnkd.in/gfs_E9FX Code: https://lnkd.in/gRW_vBFV We welcome community Gradio implementations for Vader-Videocrafter, Vader-Open-Sora, and Vader-Modelscope. You can request for GPU grants for your demo submissions. Start today: Gradio.dev

Open-source AI strikes back with AuraFlow v0.1🤩 - Largest open-sourced flow-based T2I model with Apache 2.0 license - 6.8B parameters - DiT Encoder blocks - Better instruction following - GenEval score 0.703 with prompt enhancement 🥳 Congratulations to Simo, Batuhan & the whole fal ai team on this epic release!👏 Explore AuraFlow with the community Gradio demo: https://lnkd.in/gY27BETy Find the open-source AuraFlow model on Hugging Face Hub: https://lnkd.in/g4ttnJTw Read the fal ai official release blog: https://lnkd.in/gNiK9uYN

Real Time Object Tracking with RT-DETR🔥 Simply upload a video, set up a confidence threshold, or try the examples given in the demo 👇 Demo: https://lnkd.in/gEXMka-2 Do read Merve Noyan's amazing post on LinkedIn with more details on RT-DETR model over here: https://lnkd.in/gH6Mqc4j

LivePortrait demo is still trending on Hugging Face!🔥 Try out the Retargeting feature on the demo. Edit the eyes and lips using gradio sliders 😀 Set both ratios to 0.8 to see what's going on! LivePortrait Spaces Demo: https://lnkd.in/gXSd5VkB OR build it locally with Gradio: https://lnkd.in/g9YbD7hD

🚀Introducing LLaVA-NeXT Interleave: Now AI can understand and reason with multiple images at once! ⬇️Learn everything about Llava-Next-Interleave that you would ever need - 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 - Interleave data format unifies different tasks. - New datasets on 🤗Hub: 1️⃣M4-Instruct, high-quality dataset, 1.1M samples from domains: multi-image, video, 3D & single-image 2️⃣LLaVA-Interleave Bench - Set of tasks to evaluate multi-image capabilities LLaVA-NeXT-Interleave💪 - Attached video show how Llava-Interleave can explain jokes and understand content spread in multiple images and videos🤯 - Model has SoTA Performance, both, in multiple and single images - Matches in performance with LLaVA-NeXT for single image - Improved performance in video tasks Gradio Multimodal Demo for LLaVA-NeXT-Interleave😍 : https://lnkd.in/gAaPrQtT Models and Datasets are on 🤗@huggingface Hub: https://lnkd.in/g2JEj2Uv

It's possible to finetune a GPT-2 model😲 to directly predict the result of 15-digit multiplications without using any intermediate reasoning steps. [New Paper & Gradio implementation] Super cool demo from the authors of the paper "From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step"🔥 Research Paper: https://lnkd.in/ghCX94TJ Official Gradio demo: https://lnkd.in/gNiyewQZ

This video demo of LivePortrait is gold! 😂 Thanks for sharing with us Andy Rose

🚀 It's here! A revamped new StableAudio Gradio app with some cool features [Sound: ON🎵]- - The tool now features dynamic model loading, allowing easy addition of new finetunes - BPM and bar locking functionality added for better control over music generation - Automatically converts generated audio to MIDI format, saving both .wav and .midi files - The BPM feature can help StableAudio stick to specific bars and melodic structures - Can switch models between different finetunes (e.g., piano to EDM😀) The revamped app is designed for compatibility on multiple OS and for the ease of use for the artists/builders.

📣 Hey, heard about the new encoder-free VLM called EVE? - It supports arbitrary image resolutions similar to Fuyu-8b - Performs better than Fuyu-8b on various benchmarks - EVE uses 35M publicly accessible data for training - EVE is suitable for general purpose VLM tasks unlike UI niche in case of Fuyu - MIT License 💯 The EVE paper benchmarks with Fuyu-8B, which is a similar encoder-free VLM. However, unlike Fuyu from Adept, EVE achieves sota results while being transparent about their training data and training method. Very helpful for reproducibility and further advancement. 🚀 EVE model collection- https://lnkd.in/g7PSP5dW 💡 Best way to quickly explore the model is to clone the repository and run the Gradio demo provided locally: https://lnkd.in/gzkn8zGu

Image Upscaler with Tile Controlnet 🤯 Try it out now⬇️ Demo on @huggingface: https://lnkd.in/gJW2Fca3