Lightricks · Video Inpainting
LTX-2.3 Clean Plate
LoRA (rank 32) trained on Lightricks' 22B-parameter LTX-2.3 video model removes people, vehicles and other moving subjects from a clip and reconstructs the empty background with no mask required. Gated on Hugging Face under the LTX-2 Community License; ComfyUI-wiki covered it July 19, 2026.
Open the source ↗Similar Video & Animation releases
- Viggle-Animate
Viggle AI · Character Replacement · Week 36, 2026
- DreamID-Omni
Tsinghua University · Video Editing · Week 9, 2026
- DreamID-V
ByteDance · Video Editing · Week 2, 2026
- ReCo
Research · Video Editing · Week 52, 2025
- MoCha
Orange 3DV Team · Video Editing · Week 44, 2025
- DreamOmni2
Research · Video Editing · Week 42, 2025
More from Lightricks
- The Foundation Film Is Made On
Lightricks · Text-to-Video · Week 33, 2026
- LTX-2.5
Lightricks · Text-to-Video · Week 33, 2026
- LTX-2.3 IC-LoRA Relight
Lightricks · Video Editing · Week 31, 2026
- LTX-2 Trainer
Lightricks · AI Infrastructure · Week 25, 2026
- LTX-2
Lightricks · Text-to-Video · Week 25, 2026
- LTX-Video
Lightricks · Text-to-Video · Week 19, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.