AI People Wiki

Builders & open source

Ron Mokady

VP of Research, BRIA AI

  • VP of Research, BRIA AI1

Ron Mokady is the VP of Research at BRIA AI, where Mokady directs research on and training of visual generative AI models built with licensed data. During PhD studies in computer science at Tel Aviv University with Daniel Cohen-Or and Amit H. Bermano, Mokady spent the 2020 summer at FAIR and the 2021 and 2022 summers at Google. Mokady is co-author of "Prompt-to-Prompt Image Editing with Cross Attention Control" and co-first author of "Null-text Inversion for Editing Real Images using Guided Diffusion Models", both presented by authors from Google Research and Tel Aviv University and released together in the Apache-2.0-licensed google/prompt-to-prompt repository.123456

At a glance

Current role
VP of Research
Company
BRIA AI
Sector
Company
Work listed
1
Sources cited
11
Profile reviewed

Research

Mokady's research applies machine learning to computer vision and graphics, especially image and video synthesis, with interests in disentanglement, temporal coherence, reduced supervision and the reuse of pretrained models. During PhD work at Tel Aviv University, Mokady co-authored studies of StyleGAN, including HyperStyle for inverting real images into StyleGAN for editing, a 2022 method for editing faces in real videos, and a 2022 survey of StyleGAN's architecture, methods and applications.1789

As first author, Mokady introduced ClipCap in 2021, which captions images by feeding a CLIP image embedding as a prefix to a language model. With colleagues at Google Research, Mokady then co-authored Prompt-to-Prompt, which edits generated images by controlling cross-attention, and was co-first author of Null-text Inversion, which extends such editing to real images.1023456

BRIA AI

At BRIA AI, Mokady leads research on and training of visual generative models built with licensed data. Mokady's recent co-authored papers include a 2025 study on enhancing text-to-image models with long structured captions, which introduced the open FIBO model, and 2026 papers on numeric bounding-box and color control in large text-to-image models and on generating images from contextually contradictory prompts.111

Work and contributions

  • Prompt-to-Prompt and Null-text Inversion Open-source code

    Second author of Prompt-to-Prompt (2022) and co-first author, with Amir Hertz, of Null-text Inversion (2022); both project pages list the authors with Google Research and Tel Aviv University, and the google/prompt-to-prompt repository, under the Apache License 2.0, implements Prompt-to-Prompt on Latent Diffusion and Stable Diffusion and includes Null-text Inversion for editing real images with Stable Diffusion.23456

Timeline

  1. Spent the summer at FAIR, supervised by Lior Wolf, during PhD studies.1
  2. Released ClipCap, a CLIP-prefix approach to image captioning, as first author.10
  3. Co-authored HyperStyle, a hypernetwork method for StyleGAN inversion and real image editing.7
  4. Co-authored "Stitch it in Time," a GAN-based method for facial editing of real videos.8
  5. Co-authored Prompt-to-Prompt image editing with cross-attention control.2
  6. Released Null-text Inversion for editing real images with guided diffusion models as co-first author.45
  7. Co-authored a paper on enhancing text-to-image generation with long structured captions.11

Other documented roles

Roles the sources document that are not confirmed as current.

  • Spent the 2021 and 2022 summers at Google during PhD studies, Google135
  • Spent the 2020 summer at FAIR, supervised by Lior Wolf, FAIR (Meta)1

Where they work

  • Alex NicholImage, video, and 3D generation · Computer vision
  • Amir HertzImage, video, and 3D generation · Computer vision
  • Sayak PaulImage, video, and 3D generation · Computer vision
  • Bilawal SidhuImage, video, and 3D generation · Computer vision
  • Bichen WuComputer vision · Image, video, and 3D generation
  • Tero KarrasImage, video, and 3D generation · Computer vision
  • Miika AittalaImage, video, and 3D generation · Computer vision
  • Sanja FidlerComputer vision · Image, video, and 3D generation
  • Kaiming HeComputer vision · Image, video, and 3D generation
  • Justin JohnsonComputer vision · Image, video, and 3D generation

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

11 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Ron Mokady — homepageRon Mokady · Official page · accessed Oct 21, 2026
  2. Prompt-to-Prompt Image Editing with Cross Attention Control (arXiv 2208.01626)arXiv · Paper · published Aug 2, 2022 · accessed Oct 21, 2026
  3. Prompt-to-Prompt — project page (Google Research, Tel Aviv University)Prompt-to-Prompt authors · Official page · accessed Oct 21, 2026
  4. Null-text Inversion for Editing Real Images using Guided Diffusion Models (arXiv 2211.09794)arXiv · Paper · published Nov 17, 2022 · accessed Oct 21, 2026
  5. Null-text Inversion — project page (Google Research, Tel Aviv University)Null-text Inversion authors · Official page · accessed Oct 21, 2026
  6. google/prompt-to-prompt README and LICENSE (Apache-2.0)Google (GitHub repository) · Repository · accessed Oct 21, 2026
  7. HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image EditingarXiv · Paper · published Nov 30, 2021 · accessed Oct 21, 2026
  8. Stitch it in Time: GAN-Based Facial Editing of Real VideosarXiv · Paper · published Jan 20, 2022 · accessed Oct 21, 2026
  9. State-of-the-Art in the Architecture, Methods and Applications of StyleGANarXiv · Paper · published Feb 28, 2022 · accessed Oct 21, 2026
  10. ClipCap: CLIP Prefix for Image CaptioningarXiv · Paper · published Nov 18, 2021 · accessed Oct 21, 2026
  11. Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured CaptionsarXiv · Paper · published Nov 10, 2025 · accessed Oct 21, 2026