🚨 How does Adobe Firefly Video stack up against other AI video models?
I ran the same prompts on:
• Runway Gen-3
• Hailuo AI’s MiniMax
• Luma AI Dream Machine
The results were fascinating.
5 Examples below:
The computer vision class at @MIT has nearly doubled in size since just last year!! Looking forward to teaching close to 700 students this term alongside the amazing @vincesitzmann, Mina Konakovic Lukovic, and Kaiming He 😁😁😁
Spatial Media Converter is live! It's a desktop app that converts from RGB -> depth -> stereo -> Vision Pro Spatial Photo (.HEIC). Get it here: https://t.co/d8SnhPJ2VG
Google just revealed an ABSOLUTE depth estimation model 🤯
As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image
More details below ⬇️⬇️
In a couple of weeks, we went from LCM LoRa getting about ~5fps to now ~17fps with the latest SD-Turbo distilled model. Thanks @StabilityAI the quality with SD-Turbo is incredible! Video is at normal speed. see Musk and Gates with curly hair 😅
demo: https://t.co/Nh4RJ7r09z
The Internet is too fast, I’m still crafting my catchy twits, and word is already out😂 Well then, now you have it:
RoboNinja🥷: Learning an Adaptive Cutting Policy for Multi-Material Objects https://t.co/iSVy6fEvvH
🧵👇 for a few interesting details you might have missed
I continue to be amazed at the pace of #3D research. Below, a 3D avatar is constructed by an algorithm with nothing but a short 2D vid to go off which has had no special preparation done to it. Read the full paper from @eth_en (+ soon get the code!) here: https://t.co/7qrjslHtI4
Happy to see that our #WACV2023 paper is covered by #AmazonScience! In this paper, we use active learning to actively select video samples to query, reducing annotators' click totals by 73%!