LTX-2: 19B Joint Audio-Visual Foundation Model by Lightricks
ComfyUI Wiki
LTX-2 is Lightricks' 19B parameter DiT-based audio-video foundation model for synchronized video and audio generation with open weights.
L
LTX-2
VideoAudio-VideoText-to-VideoImage-to-VideoDiTLightricksNext-generation DiT-based audio-video foundation model by Lightricks. Generates synchronized video and audio within a single 19B parameter model. Requires Gemma 3 12B text encoder. Comfy-Org repackaging includes LoRAs and quantized text encoder variants.
| Developer | Lightricks |
| Release Date | 2025-12 |
| Architecture | DiT (19B parameters) |
| License | LTX-2 Community License |
| Capabilities | Text-to-video, image-to-video, video-to-video, audio-to-video, text-to-audio |
| Required Text Encoder | Gemma 3 12B IT |
Guides and workflows related to this model series.
ComfyUI-LTXVideo: LTX Video Workflow Guide for ComfyUI
Install ComfyUI-LTXVideo and run LTX Video workflows in ComfyUI: T2V, I2V and V2V with model download links and parameter tips. LTX-2 and LTX-2.3 are natively supported.
Video
Comments
Sign in with GitHub to join the discussion.