Today we’re introducing Veo 2 in LTX Studio . We’re giving you the flexibility to switch between models and the most cost-effective way to generate with Veo 2.

LTX Studio is incredible for: → Rapid concept development for ads, films, and trailers → Auto-generating pitch decks and polished storyboards → Visualizing entire narratives with AI co-pilot precision And now LTX Studio just integrated Veo 2 generations at the lowest-cost

Join Corbett Drummey on the ground at Upscale Conf 🙌 Catch him to talk real AI and hear what we're doing to make creativity available at scale.

Today we’re introducing our latest open source video model—and it’s a big one. This release sets a new bar for speed, quality, and control. It’s faster than anything in its class, packed with new features, and ready to run on your own hardware. Let’s break it down 👇 1/7

We’re excited to launch our new model — LTXV-13B! 💫 LTXV-13B is our most advanced open-source video model yet, and a major leap forward in quality, speed, and accessibility. The future of generative video is here — and it’s fast!

AI video just got a major upgrade. Our latest breakthrough makes generation 30x faster, with no high-end GPUs required. More speed. Less cost. Same creative power. Read the full story by Michael Nuñez VentureBeat venturebeat.com/ai/lightricks-…

חברת Lightricks הישראלית שחררה מודל וידאו בקוד פתוח שנראה ממש מרשים. הוא יחסית קטן (13B) אבל עם ביצועים יפים. ועוד נקודות מעניינית: אפשר להריץ אותו על חומרה בסיסית והוא מאוד מהיר.

What a difference 2 weeks can make. We launched Veo 2, released LTX Video 13B, and brought them together with LTXV Turbo in a single platform. Three powerful models. One creative workflow. All in LTX Studio.

6 notable AI models of the week: ▪️ Gemini 2.5 Pro and Gemini Flash, Google ▪️ LTX-Video from Lightricks ▪️ @NVIDIA Open Code Reasoning LLMs ▪️ Parakeet-TDT-0.6b-v2, @NVIDIA ▪️ Mistral AI Medium 3 ▪️ LLaMA-Omni 2 🧵

2. LTX-Video from Lightricks Enables real-time, high-quality text-to-video and image-to-video generation using a diffusion-based pipeline with 30 FPS output It's optimized for resolution and speed with quantized and distilled versions for different compute needs

Today we're launching three new LoRAs for our open source video model, LTX Video! 🕺 Pose LoRA 🏞️ Depth LoRA ✏️ Canny LoRA Get unprecedented control over your AI videos and train new control types with just a few samples on consumer hardware. Details below 👇

Today we're launching three new #LoRAs for our open source video model, LTX Video! Pose LoRA, Depth LoRA & Canny LoRA! Get unprecedented control over your #AI videos and train new control types with just a few samples on consumer hardware. ✨

60-second AI video generation just got unlocked! LTXV is the first model to generate native long-form video, with controllability that beats every open source model. - 8× longer than typical gen video - 10–100× faster & cheaper - Runs even on consumer GPUs - Pose, depth &

Coming soon.

"LTXV...can now generate clips over 60 seconds long, eight times the current standard length for AI video". Read all about our latest update to LTX Video by Charlie Fink at Forbes forbes.com/sites/charlief…