Training logo

Training

Free

Train and fine-tune LTX-2 for audio-video generation.

FreeFree tier
Inputs: text, image, video, audioOutputs: video, audio
Type
Open Source
Company
Lightricks

About Training

LTX-2 Trainer is an open-source package by Lightricks for training and fine-tuning the LTX-2 audio-video generation model. It supports LoRA training and full fine-tuning with a flexible conditioning framework that covers text-to-video, text-to-audio, image-to-video, video extension, audio extension, video inpainting, audio inpainting, video outpainting, IC-LoRA for video, audio, and joint audio-video references, audio-to-video, and video-to-audio. The trainer includes a quick start guide, dataset preparation instructions, configuration reference, and troubleshooting guide. It requires an LTX-2 model checkpoint, a Gemma text encoder, Linux with CUDA 13+, and an Nvidia GPU with 80GB+ VRAM for standard config, with a low VRAM mode available for GPUs like the RTX 5090 with 32GB VRAM.

Key Features

LoRA training and full fine-tuning support
Flexible conditioning framework: text-to-video, text-to-audio, image-to-video, video extension, audio extension, video inpainting, audio inpainting, video outpainting
IC-LoRA for video, audio, and joint audio-video references
Audio-to-video and video-to-audio generation
Low VRAM mode with INT8 quantization for GPUs with 32GB VRAM
Agent-assisted training via train-model repository skill
Comprehensive documentation including quick start, dataset prep, and troubleshooting guides

Pros & Cons

Pros
  • Open-source and free to use
  • Supports multiple training modes (LoRA, full fine-tuning)
  • Flexible conditioning for various input-output combinations
  • Low VRAM configuration allows use on consumer GPUs like RTX 5090
  • Active community on Discord and GitHub for support and collaboration
  • Agent-assisted training automates data probing, mode selection, and monitoring
Cons
  • Standard configuration requires Nvidia GPU with 80GB+ VRAM
  • Only supports Linux with CUDA 13+ (no Windows or macOS native support)
  • Requires separate model checkpoints (LTX-2 and Gemma text encoder) to be downloaded
  • Limited to the LTX-2 model architecture; not a general-purpose trainer

Best For

Fine-tuning LTX-2 for custom video generation tasksTraining LoRAs for specific styles or concepts in video and audioExtending existing video or audio clipsInpainting and outpainting video and audio contentGenerating audio from video or video from audioResearch and development in multimodal generation

FAQ

What hardware is recommended for LTX-2 Trainer?
The standard config requires an Nvidia GPU with 80GB+ VRAM and Linux with CUDA 13+. For GPUs with 32GB VRAM (e.g., RTX 5090), a low VRAM config with INT8 quantization is available.
Is LTX-2 Trainer free to use?
Yes, LTX-2 Trainer is open-source and free to use.