Ohad Fried

[Rotem Shalev-Arkushin @rotemsh3]

Thrilled to share that our paper ImageRAG has been accepted to #ICLR2026 🤩🇧🇷
Check it out: https://t.co/gSCQSRYizt

@RinonGal @ohadf @bermano_h

[Omri Avrahami @OmriAvr]

I'm happy to share that Stable Flow has been accepted to #CVPR2025 🥳
Source code is available at https://t.co/03ZVzf5MRn

[Rotem Shalev-Arkushin @rotemsh3]

Excited to introduce our new work: ImageRAG 🖼️✨
https://t.co/k6ieQYigDu

We enhance off-the-shelf generative models with Retrieval-Augmented Generation (RAG) for unknown concept generation, using a VLM-based approach that’s easy to integrate with new & existing models!

[1/3]

[Omri Avrahami @OmriAvr]

👨‍💻 Happy to update that the official code implementation for Stable Flow is available!
https://t.co/IH4kkRtYDp

[Omri Avrahami @OmriAvr]

[1/10] 🚨 We present our recent @Snap project: Stable Flow --- A training-free method that performs various types of image editing operations (e.g., non-rigid editing, object addition and replacement) using flow models.
Project page: https://t.co/g0Naul2hoQ

[Sigal Raab @sigal_raab]

🔔🔔Thrilled to share #MoMo [@SIGGRAPHAsia 2024 🥳🎉]: Exploring the attention space of #MotionDiffusionModels. Our training-free method enables cool applications like this motion transfer 🐒🐒.
https://t.co/euqSM9Ceij

[Omri Avrahami @OmriAvr]

[1/7] 📜 I can finally share that our recent @NVIDIA project DiffUHaul --- A Training-Free Method for Object Dragging in Images has been accepted to #SIGGRAPHAsia2024 🎉.
Project Page: https://t.co/PPZKi1OwR9

[Omri Avrahami @OmriAvr]

Can finally share that our The Chosen One paper about consistent characters generation has been accepted to #SIGGRAPH2024 🎉

More details are available here: https://t.co/RMqVqWRW9a

Thanks @AK for sharing 🙏

[AK @_akhaliq]

Differential Diffusion

Giving Each Pixel Its Strength

Text-based image editing has advanced significantly in recent years. With the rise of diffusion models, image editing via textual instructions has become ubiquitous.

[Omri Avrahami @OmriAvr]

[1/9] 🚨 We present our recent @GoogleAI project: The Chosen One --- a fully automated solution for the task of consistent character generation in text-to-image diffusion models 🧑‍🎨.

Project Page: https://t.co/JfMvAfnrad

[Omri Avrahami @OmriAvr]

🧑‍💻Happy to update you that the official implementation of Break-A-Scene is publicly available at: https://t.co/GsqgBbRU14

[Omri Avrahami @OmriAvr]

[1/8] I'm so happy to share that our Break-A-Scene paper from @GoogleAI got accepted to #SIGGRAPHAsia2023!

TL;DR: Given a single image with multiple visual concepts, our method can "break" the image by learning a distinct token for each concept.
https://t.co/Q50nXgJZPc

[Omri Avrahami @OmriAvr]

[1/5] I'm happy to share that our Blended Latent Diffusion paper has been (finally!) accepted to #SIGGRAPH2023 🥳
TL;DR: We present a method that adapts a latent text-to-image model for a local text-driven image editing method
Project Page: https://t.co/fIaPK4rgrc

[Omri Avrahami @OmriAvr]

[1/5] Always wondered what people see when looking at a Rorschach test?
SpaText - our recent #CVPR2023 paper from @MetaAI may give you a sneak peek!

TL;DR: We extend text-to-image models with region-specific textual controllability.
Project Page: https://t.co/QNnfgn3d9m

[Omri Avrahami @OmriAvr]

[1/n] I am happy to share that our GAN Cocktail paper was accepted to #ECCV2022 @eccvconf!
Many thanks to my great supervisors @DaniLischinski and @ohadf!
The project page is available at: https://t.co/6EKlAke9rV

[Omri Avrahami @OmriAvr]

I'm excited to share that our Blended Diffusion paper has been accepted to #CVPR2022!
Thanks to my supervisors @DaniLischinski and @ohadf!

Project page (code included): https://t.co/rONZseH0Ot

[Justus Thies @JustusThies]

Our course on Advances in Neural Rendering is now freely available on YouTube!

Check out the amazing talks about the ongoing revolution of computer graphics!

Part I: https://t.co/NbdgrzidI3
Part II: https://t.co/inOw5DSGol

@_atewari @ohadf @MZollhoefer

[Roy Or-El @royorel]

Check out our latest work...

[Communications of the ACM @CACMmag]

"Editing Self-Image," by @ohadf, @jsquare, Adam Finkelstein, and @magrawala, examines the ubiquity of selfies, the rise of digital photo manipulation technologies, and their effect on self-perception. https://t.co/Db89AmlUNs

[Ohad Fried @ohadf]

We created a new way to edit video. Check it out: https://t.co/wwFgcCxQHH