Itay Chachy

Generative AI Researcher @ Lightricks

[LTX.io @ltx_io]

Introducing LTX-2.5, the world model the world builds on.

One of the biggest upgrades yet to the model already powering film, robotics, and real-time workflows. Higher pixel fidelity, multishot scenes that hold together across cuts, and a pretrained foundation built to be finetuned across domains.

Plus: Diffusion Fidelity Rendering, a new rendering approach built for pixel quality that holds up frame by frame, even on a cinema screen.

This isn't a tool you rent. It's a foundation you build on, open and yours.

[Mickey Finkelson @mikikiFin]

1/7
New paper 🧵 ScenA generates a multi-speaker audio scene: overlapping speech, laughter, real room noise, from a text description and a few reference voices.

When trained in the obvious way, it ignores the text and decides who speaks on its own. We found out why and fixed it.

[Guy Yariv @guy_yariv]

Our paper:
"LaMI: Augmenting Large Language Models via Late Multi-Image Fusion"

has been selected for an Oral Presentation at #ACL2026!

LaMI boosts LLM visual commonsense by generating complementary images from a text prompt and late-fusing their evidence into the prediction
🧵

[Roni Itkin @ItkRoni]

We introduce 🌍GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens.🌍

Most feed-forward 3DGS methods still start from pixel, voxel, or dense view-aligned primitives.
We take a different route: align first, decode later. 🧵👇

[Zeev Farbman @ZeevFarbman]

https://t.co/iB8vUIJxvI

[Gal Fiebelman @GalFiebelman]

Excited to announce that "Let it Snow!" has been accepted to #CVPR2026!🎉

We present a framework for scene-wide dynamic editing of static 3D Gaussian Splatting scenes with dynamic weather effects.

https://t.co/578C2u20hm
[1/5]

[LTX @ltx_model]

LTX-2.3 is here.

For decades, creative software has been defined by its interface. We think the next era gets defined by the engine underneath.

LTX-2.3 is a major engine upgrade:
→ Sharper detail
→ Stronger motion
→ Cleaner audio
→ Native vertical format

[david shavin @david_shavin]

[4/4] 🙏Had the privilege of working with @BenaimSagie. Check out details here:
📄 𝗔𝗿𝗫𝗶𝘃: https://t.co/W6yqnMOkG5
🌐 𝗣𝗿𝗼𝗷𝗲𝗰𝘁 𝗣𝗮𝗴𝗲: https://t.co/d5q7K3U2tt
💻 𝗚𝗶𝘁𝗛𝘂𝗯 𝗥𝗲𝗽𝗼: https://t.co/Xqs49mmHht
✍️ 𝗠𝗲𝗱𝗶𝘂𝗺 𝗗𝗲𝗲𝗽 𝗗𝗶𝘃𝗲: https://t.co/ku63ZbY5Eb

[Guy Yariv @guy_yariv]

We present DyPE, a framework for ultra high resolution image generation.
DyPE adjusts positional embeddings to evolve dynamically with the spectral progression of diffusion.
This lets pre-trained DiTs create images with 16M+ pixels without retraining or extra inference cost.
🧵👇

[LTX @ltx_model]

Introducing LTX-2: the most complete open-source AI creative engine.

- Synchronized audio and video generation
- Native 4K fidelity, up to 50 fps and 10 s+ sequences
- API-first design for seamless integration into creative pipelines
- Runs efficiently on consumer GPUs
- Fully open and accessible, with weights releasing later this year

[Yosef Dayani @YosefDay]

[1/10] 🤔 What if you wanted to generate a 3D model of a “Bolognese dog” 🐕 or a “Labubu doll” 🧸?
Try it with existing text-to-3D models → they collapse.
Why? These concepts are rare or new, and the model has never seen them.

🚀 Our solution: MV-RAG

See details below ⬇️

[David Dinkevich @DavidDinkevich]

[1/6] 🎬 New paper: Story2Board
We guide diffusion models to generate consistent, expressive storyboards--no training needed.
By mixing attention-aligned tokens across panels, we reinforce character identity without hurting layout diversity.
🌐 https://t.co/aRG81nu5qK

[Itay Chachy @ItayChachy]

[10/10] 🙌Shoutout to my amazing collaborators @guy_yariv , @BenaimSagie.

[Itay Chachy @ItayChachy]

[1/10]🚨 Introducing RewardSDS! 🚨
Standard SDS-based text-to-3D methods struggle with fine-grained alignment to user intent, often leading to artifacts or misaligned generations.
Our solution 👇

[Itay Chachy @ItayChachy]

[9/10] 📖Check out our full paper for details, experiments, and more results: https://t.co/FPiZkRw1wi.