Or Patashnik

ACEdit: Stable Multi-Turn Image Editing via Asymmetric Conditioning

Sara Dorfman, Nir Goren, Gal Barak +2

Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introduces small distribut…

Latent-Identity Tuning in Text-to-Image Personalization Models

Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor +2

Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editi…

RealMaster: Lifting Rendered Scenes into Photorealistic Video

Dana Cohen-Bar, Ido Sobol, Raphael Bensadoun +5

State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Fu…

Tuning-free Visual Effect Transfer across Videos

Maxwell Jones, Rameen Abdal, Or Patashnik +4

We present RefVFX, a new framework that transfers complex temporal effects from a reference video onto a target video or image in a feed-forward manner. While existing methods exce…

SemanticMoments: Training-Free Motion Similarity via Third Moment Features

Saar Huberman, Kfir Goldberg, Or Patashnik +2

Retrieving videos based on semantic motion is a fundamental, yet unsolved, problem. Existing video representation approaches overly rely on static appearance and scene context rath…

Continuous Control of Editing Models via Adaptive-Origin Guidance

Alon Wolf, Chen Katzir, Kfir Aberman +1

Diffusion-based editing models have emerged as a powerful tool for semantic image and video manipulation. However, existing models lack a mechanism for smoothly controlling the int…

In-Context Sync-LoRA for Portrait Video Editing

Sagi Polaczek, Or Patashnik, Ali Mahdavi-Amiri +1

Editing portrait videos is a challenging task that requires flexible yet precise control over a wide range of modifications, such as appearance changes, expression edits, or the ad…

DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models

Mor Ventura, Michael Toker, Or Patashnik +2

Text-to-Image (T2I) models have advanced rapidly, yet they remain vulnerable to semantic leakage, the unintended transfer of semantically related features between distinct entities…

SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder

Ronen Kamenetsky, Sara Dorfman, Daniel Garibi +3

Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two prop…

NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models

Nir Goren, Oren Katzir, Abhinav Nakarmi +3

With the rapid adoption of diffusion models for visual content generation, proving authorship and protecting copyright have become critical. This challenge is particularly importan…

Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing

Rishubh Parihar, Or Patashnik, Daniil Ostashev +3

Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instructions limits fine-grained cont…

Scaling Group Inference for Diverse and High-Quality Generation

Gaurav Parmar, Or Patashnik, Daniil Ostashev +4

Generative models typically sample outputs independently, and recent inference-time guidance and scaling algorithms focus on improving the quality of individual samples. However, i…

Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA

Rameen Abdal, Or Patashnik, Ekaterina Deyneka +5

Recent advances in text-to-video generation have enabled high-quality synthesis from text and image prompts. While the personalization of dynamic concepts, which capture subject-sp…

Image Generation from Contextually-Contradictory Prompts

Saar Huberman, Or Patashnik, Omer Dahary +2

Text-to-image diffusion models excel at generating high-quality, diverse images from natural language prompts. However, they often fail to produce semantically accurate results whe…

Be Decisive: Noise-Induced Layouts for Multi-Subject Generation

Omer Dahary, Yehonathan Cohen, Or Patashnik +2

Generating multiple distinct subjects remains a challenge for existing text-to-image diffusion models. Complex prompts often lead to subject leakage, causing inaccuracies in quanti…

Tight Inversion: Image-Conditioned Inversion for Real Image Editing

Edo Kadosh, Nir Goren, Or Patashnik +2

Text-to-image diffusion models offer powerful image editing capabilities. To edit real images, many methods rely on the inversion of the image into Gaussian noise. A common approac…