Omri Avrahami
I hold a Ph.D. in Computer Science from the Hebrew University of Jerusalem, where I had the privilege of being jointly supervised by Prof. Dani Lischinski and Prof. Ohad Fried.
Currently, I am a Research Scientist at Runway focusing on generative video models. Previously, I have worked as a Research Scientist at Snap Research, NVIDIA Research, Google Research, Facebook AI Research (FAIR), and Lightricks.
My research interests include machine learning, computer vision, and generative models. More specifically, I am interested in developing new tools for content synthesis and editing --- known popularly as Generative AI.
Solaris is an interface world model that generates an interactive UI, frame by frame, in response to user actions. It treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds.
Aleph 2.0 introduces several new and updated model capabilities: working with up to 30 seconds of 1080p video, localized edits with precise input video preservation, image-level control over video edits, and editing across multiple shots at once.
Runway Aleph is a state-of-the-art in-context video model, setting a new frontier for multi-task visual generation, with the ability to perform a wide range of edits on an input video such as adding, removing, and transforming objects, generating any angle of a scene, and modifying style and lighting, among many other tasks.
A training-free storyboard generation that balances identity consistency with cinematic layout diversity.
A training-free editing method that is able to perform various types of image editing operations, including non-rigid editing, object addition, object removal, and global scene editing.
An image editing method that that given a click and a prompt, infers the desired area to edit.
Given an image with an object, our method can seamlessly relocate it within the scene.
Prompt aligned personalization allow rich and complex scene generation, including all elements of a condition prompt.
Given a text prompt describing a character, our method distills a representation that enables consistent depiction of the same character in novel contexts.
Given a single image with multiple concepts, annotated by loose segmentation masks, our method can learn a distinct token for each concept, and use natural language guidance to re-synthesize the individual concepts or combinations of them in various contexts.
Given a NeRF scene, our pipeline trains a NeRF generator model guided by a similarity loss defined by a language-image model such as CLIP, to synthesize a new object inside a user-specified ROI.
We suggest a new method for text-to-image generation using open-vocabulary scene control.
We present an accelerated solution to the task of local text-driven editing of generic images, where the desired edits are confined to a user-provided mask.
We introduce a solution for performing local (region-based) edits in generic natural images, based on a natural language description along with an ROI mask.
We tackle the problem of model merging, given two constraints that often come up in the real world: (1) no access to the original training data, and (2) without increasing the size of the neural network.
