🚀 Era3D: A new AI model that creates high-res 🗿3D images from multiple viewpoints using just one input image!🌄

- Generates high-quality images up to 512×512 pixels🎯
- Uses efficient row-wise attention to reduce computation⚡
- 12x more efficient than sota methods💪

🙋🏻‍♂️NVIDIA AI just released a cool EMBEDDING model , that's 'instruction' based !
that means you can use it with LlamaIndex 🦙 instructor embeddings function,
or try it out on Hugging Face directly with my little Gradio demo :
huggingface.co/spaces/Tonic/N…
this is the future !

🔥🔥𝐌𝐮𝐬𝐞𝐏𝐨𝐬𝐞 - Generate Videos from an Image and Pose-sequences!!

🤩 The model can generate dance videos for any human (like) characters. Result's quality exceeds almost all current open-source models. Details👇

Thanks to github user 𝚖𝚊𝚕𝚝𝚎𝚗𝚕𝚣 , you can now set a starting page number in the Gradio PDF component!

Try it out with 𝚙𝚒𝚙 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚐𝚛𝚊𝚍𝚒𝚘-𝚙𝚍𝚏==0.0.8

🤯 Taking Virtual Try-On to the next level!

🚀 I2VEdit propagates edits from a single frame to the entire video.

🤯 SeemoRe: An Efficient (runs on CPU) Super-Resolution (SR) model

🚀 ICML 2024; Official demo on Spaces!🔥Details & links👇

🔥Best way to try out the trending Yolov10 model?

✅ Clone the official Yolov10 repo ➡️ Download the weights ➡️ Launch Gradio demo: 𝚙𝚢𝚝𝚑𝚘𝚗 𝚊𝚙𝚙.𝚙𝚢

OR

✅ Simply visit the Yolov10 Space on 🤗. Links below👇

Gradio Impressive work, Gradio. I2VEdit simplifies video editing to a single frame—exciting development for tech enthusiasts. Can't wait to see the demo in action!

Currently working on redesigning the Transformers documentation. I would love to hear what you like/dislike about it and how it can be improved!

✾ hf.co/docs/transform…