LTX is an open video generation AI model by Lightricks, now at version 2.5, with a free local trainer tool for creating character and style LoRAs.
LTX is an open video generation AI model developed by Lightricks. The company released LTX-2.5 on August 12, 2026, extending its open-model approach with multi-shot generation and HDR support. The model accepts text, image, and video inputs, generates videos with audio, and uses a Gemma 4-based custom LLM for prompt adherence plus Diffusion fidelity rendering for quality. Commercial use is permitted for companies with annual revenue under $10 million.
Earlier, on June 18, 2026, Lightricks updated LTX Trainer, the official LoRA development tool for the previous version, LTX-2.3. The update lets users create LoRA and IC-LoRA by rewriting a single configuration file, removing the need for custom code. A SKILL.md file for AI agents was also released, lowering the technical barrier for non-programmers.
Together, the stories show LTX as a free, locally-run video generation AI with a growing ecosystem of tools for customization and accessibility.
Synthesized by Yomimono from the cited Yomimono stories below, each itself
sourced, then editorially reviewed. Every
fact links the story it came from.
Aug 12
LTX released LTX-2.5, an open video generation AI model, on August 12, 2026. It supports text, image, and video inputs, generates videos with audio, and natively handles multi-shot generation. The model uses a Gemma 4-based custom LLM for prompt adherence and includes Diffusion fidelity rendering for quality. Commercial use is allowed for companies with annual revenue under $10 million.
Jun 18
Lightricks announced a major update to LTX Trainer, the official LoRA development tool for its local video generation AI LTX-2.3. The update allows users to create LoRA and IC-LoRA for multiple purposes by rewriting a single configuration file, eliminating the need for custom code. A SKILL.md file for AI agents was also released.