prithivMLmods/QIE-FRIE1.1-BBox-Object-Remover-v4

Note: The images showcased here are generated using QIE-FRIE1.1-BBox-Object-Remover-v4, a LoRA built on top of FireRed-Image-Edit-1.1 for fast and precise object removal with scene-aware reconstruction. The model is designed to remove the object highlighted inside the bounding box while naturally reconstructing the background, textures, lighting, reflections, and scene perspective behind the removed subject. It preserves the overall composition and visual consistency of the original image while minimizing visible artifacts and reconstruction errors.

The model performs efficiently for single-object and multi-object removal workflows, especially in structured photographic environments. For highly complex scenes with overlapping subjects or dense textures, standard inference settings are recommended for improved reconstruction quality.

This LoRA is materialized for research and learning purposes only. Any content generated by it is used at the user’s own risk. The authors and the hosting page disclaim any liability for content generated by this model. Users are responsible for ensuring that the model is used in a safe, ethical, and lawful manner.

Trigger Prompt

Use the following prompt to activate the object removal behavior:

Remove the red highlighted object from the scene.

Base Model

This LoRA is based on:

• FireRed-Image-Edit-1.1

Training Data

• Manually annotated bounding box and resultant dataset pairs

Download Model

You can download the model files from the Files & versions tab:

Download