LTX-2.3 22B IC-LoRA MotionDeblur

This is a MotionDeblur IC-LoRA trained on top of LTX-2.3-22b, designed to reduce (or, when possible, remove) motion blur from input video — the per-frame smearing introduced by long shutter speeds, fast subject motion, or aggressive in-camera/post motion-blur effects. It uses the blurred clip as the conditioning input and reconstructs a sharper version of the same shot. Results vary with the severity of the original blur; heavy blur is typically softened rather than fully eliminated.

It is based on the LTX-2.3 foundation model.

Model Files

ltx-2.3-22b-ic-lora-motiondeblur.safetensors

Model Details

• Base Model: LTX-2.3-22b
• Training Type: IC LoRA
• Purpose: Reduce or remove motion blur from footage
• Training Steps: 5000

🔌 Using in ComfyUI

1. Copy the LoRA weights into models/loras.
2. Use the IC-LoRA workflow from the LTX-2 ComfyUI repository.
3. Load the LoRA using the LTXICLoRALoaderModelOnly node.

License

See the LTX-2-community-license for full terms.