LTX-Video
LTX-Video is an open-source video production model based on DiT that can produce synchronized audio and video. The model features advanced features such as image-to-video conversion, multiple key square conditioning, and video extension. It can be included in workflows with ComfyUI and Diffusers integrations.
LT
Lightricks · Local AI / Self-Hosted LLM
STARS11.3K
FORKS1.2K
COMMITS89
CONTRIBUTORS10
VERSIONltx-video-0.9.1
UPDATED9 mo ago
PythonLightricksHızlı ÜretimReal-TimeApache-2.0
Common commercial products in this category: ChatGPT, Claude, Gemini
What can it do?
- You produce synchronized audio and video content in one step
- Convert from image to video and apply multiple key square conditioning
- You include it in video workflows using ComfyUI integration
User reviews
- • NeutralGitHub Issue
VRAM info
“Small passage about VRAM info would be nice :)”
- • NeutralGitHub Issue
Multi GPU inference on 13b-dev base model?
“Hi, I use single 48GB video card to run 13b model, while failed. I was wondering is there proj for multi-gpu inference?”