LTX 2.3 inference with ComfyUI¶
A streamlined and automated environment for running ComfyUI with LTX-2.3 video models, optimized for use on RunPod
Example included workflows¶
i2v¶

iv2v pose transfer DWPose¶

iv2v pose transfer SDPose (Body Ratio Mapper)¶

🔧 Features¶
- Automatic model and LoRA provisioning via environment variables.
- Kajai models no checkpoint
- Included workflows for video generation and enhancement using pre-installed custom nodes.
- Compatible with high-performance NVIDIA GPUs (CUDA 12.8).
- Compiled attentions and GPU accelerations.
- Automatic selecting bf16 or fp8 models/workflows.
- Latent preview enabled for both samplers.
- Included worflows based on RuneXX
- Lora manager
🔧 Built-in authentication¶
- ComfyUI
- Code Server
- Hugging Face API
- CivitAI API
📦 Deployment on runpod¶
📘 Tutorial¶
Pod running on L40S bf16¶

Pod running on RTX 6000 Ada bf16¶

Pod running on RTX A5000 fp8¶

Pod running on RTX 4090 fp8¶
