LTX-2.3 Audio-to-Video
Turn a still image + an audio clip into a lip-synced talking or singing avatar with LTX-2.3, Lightricks' latest video model — improved lip-sync and facial realism over the previous version.
✓ 100% free — download the workflow and run it locally.Preview
Requirements
- GPU: NVIDIA RTX 30XX/40XX/50XX (FP16)
- VRAM: 12 GB minimum, 16 GB+ recommended
- OS: Windows
- Storage: 50 GB+ free
Model downloads
- ltx-2.3 text projection (bf16) https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/text_encoders
- gemma-3-12b-it (Q4_K_XL GGUF) https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/tree/main
- LTX23 audio + video VAE (bf16) https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/vae
- ltx-2.3-22b-dev (Q3_K_S GGUF) https://huggingface.co/unsloth/LTX-2.3-GGUF/tree/main
- LTX-2.3 distilled LoRA https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/loras
- LTX-2 camera-control LoRA https://huggingface.co/Lightricks/LTX-2/tree/main
- LTX-2.3 22B diffusion models (FP8) https://huggingface.co/Lightricks/LTX-2.3-fp8/tree/main
Custom nodes
- ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager
Setup steps
- Install ComfyUI Manager + requirements; place all models in their folders.
- Load the workflow below into ComfyUI.
- Toggle sections with the Fast Groups Bypasser.
- Input an audio file + reference image, then run.
Notes & tips
- 10s 480p clip in under 4 min on an RTX 4090; higher-end GPUs do 720p+ at 24fps+.
- High-res source images improve motion + lip-sync; tune the distilled LoRA strength for motion intensity.
- Prefer one-click? LTX-2.3 installers are available.
Want the 1-click version?
Skip the manual model downloads and node installs — get a ready-to-run installer, or unlock all 75+ with Local Lab Pro.