Podcast Summary

Reshaping Workflows with Dell Pro Precision and NVIDIA RTX PRO GPUs

Episode: Live from GTC: Supercharging Next-Gen Video with Yaron Inger of Lightricks
Date: March 19, 2026
Host: Logan Lawler
Guest: Yaron Inger, Co-founder and CTO of Lightricks

Episode Overview

This episode, recorded live at NVIDIA’s GTC 2026, spotlights the transformative impact of Dell Pro Precision workstations paired with NVIDIA RTX PRO GPUs through a focused conversation with Yaron Inger, CTO and co-founder at Lightricks. The discussion centers on the evolution and real-world application of Lightricks’ LTX AI video model, especially its transition from LTX1 to the groundbreaking, open source, multimodal LTX2. Yaron reveals how these powerful workstations enable advanced AI video workflows, and underscores the importance of open source in democratizing creativity for studios and creators globally.

Key Discussion Points & Insights

Lightricks’ Evolution: From Mobile Apps to AI-First Company

Background
- Lightricks has evolved over 13 years—from popular mobile apps like Facetune to an AI-first creative company.
- In the past three years, the company shifted its focus to foundational AI video models, culminating in the release of LTX2.
- LTX2 is open source—accessible to all, with over 5 million downloads on Hugging Face ([00:40]).

"In the last three years we completely transitioned to become an AI-first company... The latest version is LTX2... ranked number one in the world doing video and audio. So multimodal. And it's also open source which is great because everybody can just download and run it."
— Yaron Inger, [00:40]

LTX2: A Major Leap Forward

Gen Over Gen Improvements
- LTX2 features massive scalability: more parameters, broader data, and—for the first time—audio support.
- The model is truly multimodal, with audio and video generation tightly integrated.
- Audio-to-video capabilities enable new creative workflows like generating music videos with character lip sync and expressions driven by the audio track.
- Efficiency: LTX2 can run both in the cloud and on consumer hardware, like the Dell Promax T2 workstation with RTX 6000 GPUs ([02:20]).

"We scaled everything... we also added the audio support which is amazing because who nowadays creates a video which is without an audio... the audio really drives the expression of the characters."
— Yaron Inger, [02:20]

Open Source Commitment
- LTX2’s weights, inference code, and training code are all open source—enabling full customization, local inference, and fine-tuning.
- Enterprise studios can run LTX2 fully on-premises, crucial for IP protection.
- The model is highly efficient and compressed, supporting both on-prem data center GPUs and consumer GPUs ([02:20]).

"We open source not just the weights, but also the inference code and the training code which allows you to fine tune the model... The ability to run locally on Prem is also something that's very, very important because it means that you can run it in your own network."
— Yaron Inger, [02:20]

Workflow Innovations and Creative Control

Key Features
- Retake Workflow: Modify part of any clip (AI-generated or real)—critical for personalized ads or nuanced content tweaks.
- The system preserves lip sync, voice, and emotional tone—even with zero additional training.
- "Video to video" transformations and depth map generation expand creative control.
- Features are driven both by internal development and an active open source community ([05:16]).

"One really great workflow is called Retake, which allows you to take an existing clip... and just modify part of that clip. ...The model knows how to fill in the blanks really amazingly well and also preserve the audio and the voice signature of the speaker with zero training."
— Yaron Inger, [05:16]

Community Impact
- Open source approach empowers community-driven extensions and integrations, rapidly expanding available features and use cases ([05:16]).

Real-World Hardware Synergy

Dell + NVIDIA RTX PRO Workstations
- LTX2 performs smoothly on Dell Pro Precision series with RTX 6000/Blackwell GPUs, enabling high-end AI video tasks even for local users.
- Flexible workflows allow mixed hardware use: e.g., low-res creation on consumer GPUs, upscaling in the cloud for efficiency and scalability ([02:20], [06:55]).

How to Get Started

Access & Documentation
- Recommended entry point: LTX.io, which aggregates downloads, documentation, and links to Hugging Face and GitHub.
- Both API and open source documentation are available ([07:16]).

"It would be best to go to LTX IO. From there go and download the model. All the links are there. Tagging face GitHub. We have online documentation for open source and for the API."
— Yaron Inger, [07:16]

Notable Quotes & Memorable Moments

"I'm not a creative by any stretch of the imagination... but it [LTX2] definitely rivals anything... you guys are kind of blowing them out of the water."
— Logan Lawler, [01:37]
"We have many control features like that, many video to video features where you can take human acting and transform it to a different video. Use depth maps to generate videos from."
— Yaron Inger, [06:18]

Key Timestamps

00:40 — Yaron introduces Lightricks, LTX, and the open source approach
02:20 — What’s new in LTX2: scaling, audio, multimodal generation, on-premise support
05:16 — Favorite workflows, Retake feature, and the value of creative flexibility
06:55 — Best ways to get started with LTX2 and find resources
07:16 — Where to download and access docs

Conclusion

This episode provided an insider’s look at the evolution and possibilities unlocked by Lightricks’ LTX2 video AI model, made possible by robust hardware from Dell and NVIDIA. The open source strategy, combined with high-end workstation capabilities, is democratizing access to cutting-edge video generation and empowering creators and enterprises alike.

To learn more or try LTX2 yourself, head to LTX.io.

Transcript

Logan (0:00)

Foreign.

Podcast Host (0:05)

Welcome to reshaping workflows with Dell Pro Precision and Nvidia, where innovation meets real world impact in high performance computing.

Logan (0:19)

This is Logan live from GTC 2026. This is day three and we're here at LTX at Light Tricks. So I'm with Yaron, also known if you've ever been to Starbucks with him. Known as Dan apparently, is what he said, not me. So first you're on. Really appreciate the time. Tell us, you know, all the listeners out there, kind of what your position is, what you do and then we'll get right into it.

Jeroen (0:40)

Okay. So hi, I'm Jeroen, co founder and CTO at Lytrix. And you know we're a company that exists for 13 years now, did a lot of apps on mobile like Facetune. In the last three years we completely transitioned to become an AI. First company started developing our own video model called LTX. The latest version is LTX2 that was released about two and a half months ago. Amazing video model, ranked number one in the world doing video and audio. So multimodal. And it's also open source which is great because everybody can just download and run it. We already have more than 5 million downloads on Hugging Face. And besides the foundational model itself, we also offer API for inference and also a product layer on top which is a one stop shop for video and image creation and storytelling called LTX Studio.

Logan (1:37)

So as you know. I did not know. I mean I work with Noah a little bit and I know LTX has been around for a little while. Right. And not a knock to your previous product, but I'd use the original version about a year ago and I mean it was good but nothing was great. Right. And I've installed the newer version and it's great. And I'm not a creative by any stretch of the imagination, but it definitely LTX rivals anything. I mean I'm not comparing your competition but like you know, Runway, like all the stuff you kind of expect, you guys are kind of blowing them out of the water. So I guess what really, and you don't have to share any proprietary secrets or anything like that, but really kind of gen over gen from like LTX1 to say LTX2. What has really changed? Like what have you done to really. I mean, because it went from good to freaking fantastic. So what really changed in that to make that jump?

Jeroen (2:20)

So basically everything we scaled everything, whether it's the number of parameters, the data and of course we also added the audio support which is amazing because who nowadays creates a video which is without an audio. And surprisingly so the audio also really affects the quality of the video because the way that we generate video is not just the video, the audio itself. And the audio generation also affects the video generation and vice versa. And so we got a ton of great feedback on features that use the model in maybe surprising ways, like audio to video, where you can maybe you have your own audio track and you want to generate a video for that, like music video for example. And then you can generate characters that sing based on that original soundtrack. And the community says that this is the best model out there for these kind of performances because the audio really drives the expression of the characters and so on. The reason going back to maybe the reason of why this is all open source. So we have various reasons. One is democratization of creativity. We think that right now, as more and more companies go closed source, it's really, really important for us and for the world, I think that to have a model that is completely open, we open source not just the weights, but also the inference code and the training code which allows you to fine tune the model. So if you have your own data, you can just use that to make a better model or a model that's customized for yourself. If you're a studio, and we have many clients that are studios that want to protect their ip, they don't want to send it over the Internet, so they want to do it on Prem. And the ability to run locally on Prem is also something that's very, very important because it means that you can run it in your own network, whether it's on data center gpu, which is worked amazing because our model is extremely efficient and very compressed. But also you can run it on consumer GPUs like we see behind us, we have a dell workstation here, T2 with RTX 6000 and it works amazingly well, which is crazy. So basically all the stack and you can also mix and match the hardware, you can run in low res, generating low resolution on consumer GPUs and then send it to the cloud for upscaling.