This is such exciting news. Another useful tool in the toolbox (timesaver too). A sneak-peak of the Adobe Firefly Video Model Coming Soon | #CommunityxAdobe youtu.be/puEgugluadk?si…

We present UniReal, a universal framework for multiple image generation and editing tasks. Webpage: xavierchen34.github.io/UniReal-Page/ Paper: arxiv.org/abs/2412.07774

🚀 LongVILA is open-sourced: our comprehensive solution for scaling long-context Visual-Language Models (VLMs) to tackle the challenges of long video understanding! 🎥📖 - Paper: arxiv.org/pdf/2408.10188 - Code: github.com/NVlabs/VILA/tr… - Models: huggingface.co/collections/Ef… 🔍 What

🚀 I am very glad to share that our work #ObjectMover is accepted by #CVPR2025! 🎉 We introduce an image editing model that enables realistic object movement/removal/insertion by leveraging a video diffusion model. Project Page: xinyu-andy.github.io/ObjMover/ How?👇

wow.. ChatGPT just dropped Image Editor you can now select an area of the image to add, remove or change things, its only available to some users now here's how to get access and some tricks:

Welcome to submit your work, see you in Hawaii! 🌴🌴

Thank you for sharing! 🥳

Thanks AK for sharing our paper! By comparing an image with its augmentations and similar images, we introduce a self-supervised-style approach to enhance the cross-image reasoning ability of VLMs.

Right after Sora2 was released, we ran an interesting comparison with LongLive, our open-source model released just two days earlier, focusing on long video generation. Since Sora2 can only generate 10s clips, we used GPT-5 for prompt engineering, enriching the inputs with

exploring how far I can push Genie 3 🤯

Excited to share our paper EditedVerse is accepted as oral to ICLR 2026! Many thanks to our amazing coauthors!! Paper Link: arxiv.org/pdf/2509.20360 Project Page: …se.s3-website-us-east-1.amazonaws.com