ComfyUI and ComfyUI-LTXVideo
About ComfyUI
Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Supports diverse generative models across image, video, audio, and 3D modalities with intelligent memory management and GPU offloading for low-VRAM systems. The architecture uses an asynchronous queue system with incremental execution—only re-computing workflow nodes that have changed—and integrates LoRAs, ControlNets, and model merging capabilities. Extensible through custom nodes and external API providers, while maintaining fully offline operation for core functionality.
About ComfyUI-LTXVideo
Lightricks/ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
Provides custom nodes for single and two-stage video generation pipelines with spatial/temporal upscaling, IC-LoRA control adapters (depth, pose, edges, motion tracking), and camera control LoRAs. Implements unified control conditioning through a single LoRA that processes downsampled latents to reduce memory overhead while maintaining quality. Integrates with ComfyUI's native LTX-2 support, leveraging both full and distilled model variants alongside specialized text encoders and LoRA modules for fine-grained motion and composition control.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work