Ali Thabet (@alitabet) header
Ali Thabet (@alitabet) profile picture

Research Manager @ Meta. Helping machines perceive the world around

Zurich, Switzerland
Joined May 2011
Photo by Ali Thabet (@alitabet)Photo by Ali Thabet (@alitabet)Photo by Ali Thabet (@alitabet)
The story behind Imagine Flash going from research to production in record time. What a fun ride it’s been to work in this project!
A fun backstory: we first demoed this breakthrough to @finkd, @Ahmad_Al_Dahle and others this February on a single node. There was so much excitement about this research that in a mere 2 months we scaled it up and today is in production available to billions via Meta AI #movefast
2
1
2
688
More Flash examples…
Today you can experience the future of image generation with our latest version of Meta AI. Offering lightning-fast speeds, stunning high-quality images, and a revolutionary new way to create and animate custom images using simple text prompts. @savitz described it pretty well: “...text-to-image queries will be created and updated in real time... It’s a remarkable show of computing power, which is going to result in massive time wasting by people everywhere." Check it out on meta.ai or in @messenger, @WhatsApp, @instagram or @facebook!
2
3
693
Imagine Flash now powers high quality real-time image generation on meta.ai and WA. Check out our paper and try it yourself!
In addition to Llama 3, today we’re also publishing a new paper: Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation ➡️ go.fb.me/g4r584 This work from GenAI researchers is enabling new image generation features in Meta AI on @WhatsApp & web.
2
2
2
16
2,616
Imagine Flash is out! High quality real-time image generation. Try it on meta.ai and WA in the US, and check out our paper: tinyurl.com/2bbxbwh6 @AIatMeta
📢Introducing Imagine Flash Buckle up! We're releasing a new model for real-time image generation. Available in meta.ai and WA. 📄 Paper: tinyurl.com/2bbxbwh6 Amazing team: J.Kohler, @schoenfeldedgar, @artsiom_s, @rsumbaly, P.Vajda, @alitabet @AIatMeta
4
1
19
1,225
Thrilled to announce that our Zurich team was directly responsible for optimizing the AI Sticker generative model. Just type in a description, and watch as it creates personalized stickers for you in IG/FB, WA. A glimpse of this in an excerpt from keynote by MZ at Meta Connect
1
2
24
3,508
Since joining Meta GenAI, our team focused on speed advancements in image synthesis. Exciting news!🚀 We've unlocked high-quality image synthesis in just ~5 sec! MZ showcased our progress at Meta Connect. Try it out with the /imagine command in our AI chatbot in FB, IG or WA
8
9
89
22,614
🚀 Exciting News!! Hard work paid off! 🙌 In #MetaConnect2023, MZ showcased our tech enabling high-res image generation in <5 seconds! 🖼️💥 Try it out on WhatsApp, Instagram, and Facebook Huge thanks to our incredible team! @alitabet @artsiom_s @schoenfeldedgar and J. Kohler.
1
10
2
56
10,276
Thrilled to see my team's work highlighted in this year's Meta Connect. The GenAI Media/Efficiency team optimizes image and video generation models to run very fast at inference team. teapaw.org/AlbertPumarola/status/… teapaw.org/artsiom_s/status/17074…
Replying to @artsiom_s
Huge shoutout to our amazing team at Meta GenAI Zurich - @alitabet @AlbertPumarola @schoenfeldedgar and Jonas Kohler!
3
11
1,129
Big shoutout to my amazing team @artsiom_s @AlbertPumarola @schoenfeldedgar and Jonas Kohler
1
116
We have released the code and weights for our #CVPR2023 paper "Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model"! code: github.com/facebookresearch/… abs: arxiv.org/abs/2304.08577 project: dulucas.github.io/agrol/ The demo is below:
4
50
3
300
35,717
Ali Thabet retweeted
Our CVPR2023 paper is finally out on arxiv🤩 this is a joint work with @artsiom_s @AlbertPumarola @alitabet @robin_kips @blacksquirrel__ during my internship at Meta. Amazing team and fantastic experience!!! Stay tuned for the code.
Our paper "Avatars Grow Legs" (CVPR 2023) is out! TL; DR: Fast Diffusion models to generate full body motions based on head and hands tracking inputs, Will release the code in a few days.
2
2
14
1,478
VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids The goal of this work it show that network-free grid-based implicit representations can achieve INR (Implicit Neural Representation)-level 3D reconstructions when incorporating suitable priors. 1/n
1
3
5
In 1 hour at #NeurIPS2022 I will be presenting VisCo-Grids, a grid-based surface reconstruction method incorporating Viscosity and Coarea priors. Joint work at @MetaAI with @AlbertPumarola, @YarivLior, @alitabet and @lipmanya research.facebook.com/public… Details in the thread 🧵
1
15
63
This week in #NeurIPS2022 we will be presenting VisCo-Grids, a grid-based surface reconstruction method incorporating Viscosity and Coarea priors. Work developed at @MetaAI with @artsiom_s, @YarivLior, @alitabet and @lipmanya. 📄PDF: research.facebook.com/public…
2
16
1
91
16 Days left for CVEU Workshop! Remember that the workshop will happen one week before the official conference. Our workshop will have an amazing line-up of speakers and two great panel discussions about the future of creative AI. Don't miss it out! Info: cveu.github.io
Excited to share that we are organizing a tutorial on Graph Machine Learning for Visual Computing on 6/20 PM this @CVPR. We have amazing speakers taking about Geometric DL, PyG and Graph ML applications in Videos, 3D, physical reasoning and Robotics! Don’t miss it! @CVPRConf
6
67
1
197
Honored to be organizing this event with @guocheng_qian, Jesus Zarzar, @GiancolaSilvio, @alitabet, Matthias Müller, @fedassa and @BernardSGhanem!
2
6