Omer Bar Tal (@omerbartal) / X

Omer Bar Tal

361 posts

Omer Bar Tal

@omerbartal

Founder @ Stealth, previously @runwayml @pika_labs @Google @WeizmannScience

New York, NY

Joined March 2016

Pinned
Omer Bar Tal
@omerbartal
Nov 6, 2025
Update: I’ve recently left Runway to start a new company! GenAI transformed how we create, but not how we experience what’s created. It’s time to rethink how we interact with intelligence. We’ve just closed a seed round with amazing top-tier investors. If you’re excited building
59K
Omer Bar Tal
@omerbartal
Jan 24, 2024
Introducing Lumiere 📽️ The new video diffusion model we've been working on @GoogleAI * Text-to-Video * Image-to-Video * Stylized Generation * Inpainting * Cinemagraphs and more 🎨 W/ amazing team incl. @hila_chefer @omer_tov @InbarMosseri @talidekel @DeqingSun @oliver_wang2
00:00
189K
Omer Bar Tal
@omerbartal
Feb 6, 2025
Excited to introduce Pikadditions! Upload any video and make it more engaging by adding any object/character to it, based on an image reference. Check it out at pika dot art! @pika_labs
00:00
34K
Omer Bar Tal
@omerbartal
Nov 9, 2022
Played with optimizing Neural Atlases through Stable Diffusion. So much fun! Here are a few examples of video edits: @RafailFridman @DanahYatim
00:00
Omer Bar Tal
@omerbartal
Feb 17, 2023
Excited to share "MultiDiffusion"! A controlled image generation framework w/ pre-trained text-to-image diffusion model. * Spatial guidance controls (bounding boxes/masks) * Arbitrary aspect ratios (huge Panoramas!) NO training NO finetuning. [1/3]@YarivLior @lipmanya @talidekel
00:00
89K
Omer Bar Tal
@omerbartal
Nov 29, 2023
Text2video models are getting interesting!📽️ Check out how we leverage their space-time features in a zero-shot manner for transferring motion across objects and scenes! diffusion-motion-transfer.github.io Led by @DanahYatim @RafailFridman,@yoni_kasten @talidekel [1/3]
00:00
63K
Omer Bar Tal
@omerbartal
Sep 4, 2023
The code and demo for TokenFlow are both released! 🥳 Check out our work for consistent video editing with a fixed text-to-image diffusion 🎥 Webpage: diffusion-tokenflow.github.io Demo: huggingface.co/spaces/weizman… @GeyerMichal @OneViTaDay @talidekel Thanks @linoy_tsaban @multimodalart!
00:00
122K
Omer Bar Tal
@omerbartal
Apr 9, 2025
I’m excited to join Runway! There’s a lot to explore at the edges of media and creativity, and it’s great time to rethink storytelling which is core at Runway’s mission. I’ll be moving to NYC as well - if you wanna grab coffee, text me :)
31K
Omer Bar Tal
@omerbartal
Nov 11, 2023
ICLR 2024 stats 💡 * 451 titles contain 'Diffusion' * 208 titles contain 'LLM' * 6 titles contain 'ChatGPT' * 25 titles contain 'NeRF' * 41 titles contain 'GAN' * 15 titles contain 'All you need' 🧐 * 22 titles contain 'Dream' * 6 titles contain 'Magic' #ICLR2024 @iclr_conf
73K
Omer Bar Tal
@omerbartal
Feb 22, 2024
Thrilled to share that I've joined @pika_labs as Founding Scientist! It's exciting times in video generation and AI, and we're committed to unlock new capabilities and empower creative content creation. Delighted to work with the most talented @demi_guo_ @chenlin_meng🚀
61K
Omer Bar Tal
@omerbartal
Jul 25, 2025
Excited to introduce *Runway Aleph* -- the first general purpose visual generation model. We designed a model that can be conditioned on input videos/images/text, and be intuitively used for ANY kind of editing task! Huge shoutout to my insanely talented team!
Runway
@runwayml
Jul 25, 2025
Introducing Runway Aleph, a new way to edit, transform and generate video. 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
00:00
17K
Omer Bar Tal
@omerbartal
Dec 13, 2024
Meet Pika 2.0! Besides improved quality and motion, our new model can embed user-provided concepts into the generated videos, without any training! Combined with an unprecedented level of text-alignment, you can now create YOUR OWN personalized content with minimal effort 🎬
00:00
12K
Omer Bar Tal
@omerbartal
Feb 20, 2023
Replying to @omerbartal
MultiDiffusion is now integrated into diffusers 🚀 currently text2panorama is supported, spatial controls (masks/bounding boxes)- soon :) demo: huggingface.co/spaces/weizman… official repo: github.com/omerbt/MultiDi… Thanks @RisingSayak @_akhaliq and @huggingface team!
27K
Omer Bar Tal
@omerbartal
Jul 26, 2025
Editing semitransparent effects in video usually requires layering and precise integration. Inpainting alone isn’t enough as content behind the mask shifts. We found Aleph can handle this zero-shot. No task-specific training. Truly a generalist model. Can’t wait to see what else
00:00
00:00
9.3K