Kfir Goldberg

I work as a researcher at Bria AI, focusing on image and video generation. Outside of that, I independently explore image generation and computational creativity.

Publications

2026

Inspiration Seeds: Learning Non-Literal Visual Combinations for Generative Exploration Kfir Goldberg, Elad Richardson, Yael Vinker paper page
SemanticMoments: Training-Free Motion Similarity via Third Moment Features Saar Huberman, Kfir Goldberg, Or Patashnik, Sagie Benaim, Ron Mokady paper

2025

Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions Eyal Gutflaish, Eliran Kachlon, Hezi Zisman, Tal Hacham, Nimrod Sarid, Alexander Visheratin, Saar Huberman, Gal Davidi, Guy Bukchin, Kfir Goldberg, Ron Mokady paper code
Piece it Together: Part-Based Concepting with IP-Priors Elad Richardson, Kfir Goldberg, Yuval Alaluf, Daniel Cohen-Or paper page

2023

ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints Elad Richardson, Kfir Goldberg, Yuval Alaluf, Daniel Cohen-Or paper page

2020

Rethinking FUN: Frequency-Domain Utilization Networks Kfir Goldberg, Stav Shapiro, Elad Richardson, Shai Avidan paper code

Projects

Fibo-Edit

Fibo-Edit

Image editing with structured JSON prompts and native masking support.

code

AnyPathLib

AnyPathLib

Unified Python API for file operations across cloud storage providers.

code

Zero-to-Wan

Zero-to-Wan

Minimalistic codebase for fine-tuning the Wan2.1-1.3B video generation model.

code

PeerXiv

PeerXiv

A platform for peer review of preprints.

page