Nir Zabari‎

AI Researcher | Co-author of LTXV | Generative AI | Blind Coding
GTA 6 release date: November 19, 2026

[Nir Zabari‎ @nirzabari]

LTX-2.3 is live!
A huge leap forward from LTX-2 - sharper visuals, much cleaner audio, rock-solid consistency, and full vertical support.

Built directly from user feedback to power real production workflows.

Best of all - open weights, ready to roll.

#OpenSourceAI #GenerativeAI #LTX
@ltx_model

[LTX.io @ltx_io]

Most AI video tools stop at prompting, but LTX goes a layer deeper.

Introducing the new LTX Trainer.

Train LoRAs and IC-LoRAs across video, audio, cross-modal, and reference-conditioned workflows from a single framework.

Plus:
• New agentic skill
• Flexible conditioning
• Free IC-LoRAs
• Fully open source

Most models are generic.

The best ones become yours.

GitHub: https://t.co/mPnUeYVwEW
Documentation: https://t.co/8P10XMf6ZB
HuggingFace: https://t.co/sDtwqeAaAp

[fal @fal]

New open-source LoRA built in-house: LTX2.3 Audio Reactive LoRA.

Built for music-driven video generation: stronger beat sync, graphic texture, color separation, light pulses, particles, and shapes that move with the track.

Model:
https://t.co/MJFO7iqOAs

[Nir Zabari‎ @nirzabari]

@RisingSayak @Lightricks Really cool! 👏👏

[Nir Zabari‎ @nirzabari]

@ostrisai Cool. It's like a visual "refusal"

[Nir Zabari‎ @nirzabari]

@0xMovez Tokens usage will go to the clouds with loops all day long lol

[Nir Zabari‎ @nirzabari]

Friction = Opportunity

[Nir Zabari‎ @nirzabari]

@OmriAvr Great job!👏

[Eliya Habba @EliyaHabba]

New datasets keep coming,
New models keep coming.

Frustrating!
How can we evaluate everything on everything?
How do we keep scores comparable over time?

We propose a way to grow benchmark suites without losing comparability.

Details:👇🧵

[Nir Zabari‎ @nirzabari]

Better data alone didn’t cause this breakthrough for sure

[OpenAI @OpenAI]

What makes ChatGPT Images 2.0 a state-of-the-art image generation model?

Researchers behind the model explain. A thread:

Thinking & Intelligence in ChatGPT Images 2.0, demonstrated by @ayaanzhaque

[Nir Zabari‎ @nirzabari]

@rasbt GREAT writeup! Learnt something new.
I wrote a similar one too:
https://t.co/vgRx80neDy

[Nir Zabari‎ @nirzabari]

@boazbe Taste is all that’s left

[Nir Zabari‎ @nirzabari]

LTX ❤️ Open source.

[Ostris @ostrisai]

I trained this @ltx_model LTX 2.3 LoRA of George Costanza at home on my 5090 in about a day with AI Toolkit. I generated this 30 second video with @ComfyUI on my 5090 in 6 minutes. Open source is, always has been, and always will be, the future of generative AI. (SOUND ON)

[Ostris @ostrisai]

I trained this @ltx_model LTX 2.3 LoRA of George Costanza at home on my 5090 in about a day with AI Toolkit. I generated this 30 second video with @ComfyUI on my 5090 in 6 minutes. Open source is, always has been, and always will be, the future of generative AI. (SOUND ON)

[Nir Zabari‎ @nirzabari]

@HubermanSaar @DanahYatim Cool work GG!

[Nir Zabari‎ @nirzabari]

Cursor routing every model = the most diverse coding conversation data in the world.

They might end up training a better coding model than the labs themselves.

[Cursor @cursor_ai]

Composer 2 is now available in Cursor.

[Zeev Farbman @ZeevFarbman]

https://t.co/iB8vUIJxvI

[Nir Zabari‎ @nirzabari]

@giffmana @CSProfKGD For sure mainly better data, focus on human etc

[Nir Zabari‎ @nirzabari]

@GalFiebelman Really cool!

[Nir Zabari‎ @nirzabari]

@nir_benz Cursor with the right AGENTS.md beats both

[Nir Zabari‎ @nirzabari]

@urieli17 @Lightricks כמה איטרציות נוספות ואנשים יריצו ג׳ינרוטי וידאו באיכות קולנועית מקומית על המחשב שלהם.
בעיניי זה עניין של 1–3 שנים.

גילוי נאות: חלק מהצוות שעובד על המודל בלייטריקס.