Modelpublic

prithivMLmods/Qwen-Image-2.1-Object-Mover-Bbox-Preview

sourceHugging Faceotherupdated 8h agoView on Hugging Face

1likes

Model Card

Qwen-Image-2.1-Object-Mover-Bbox-Preview

Qwen-Image-2.1-Object-Mover-Bbox-Preview is a preview LoRA adapter for Qwen-Image-2.1, designed for object manipulation using bounding box guidance. The adapter moves an object highlighted by a red bounding box to a target location indicated by another red bounding box while attempting to preserve the object's appearance, surrounding textures, lighting, shadows, perspective, and overall image consistency.

[!NOTE] This is an experimental preview model. Results may vary depending on the image, object, bounding boxes, target location, and surrounding context.

Model Details

—Base Model: Qwen/Qwen-Image-2.1
—Adapter: Qwen-Image-2.1-Object-Mover-Bbox-Preview
—Model Type: LoRA / Adapter
—Model Status: Preview / Experimental
—Created by: prithivMLmods

Training Specifications

Parameter	Configuration
Dataset	40 pairs of high-quality images with bounding box annotations and manually manipulated resultant images
Save Precision	BF16
Learning Rate	`1e-4`
Optimizer	AdamW
Network Dimension (Rank)	16
Total Steps	5000
Trigger Prompt	`Move the object highlighted in the red box to the location indicated by the other red box in the scene.`

Download

Download the model files from the Files & versions tab:

Download Qwen-Image-2.1-Object-Mover-Bbox-Preview

Usage

Load the LoRA adapter with Qwen-Image-2.1 and provide an image containing two red bounding boxes: one highlighting the object to be moved and another indicating its target location.

Use the trigger prompt:

text

Move the object highlighted in the red box to the location indicated by the other red box in the scene.

For best results, use clear bounding boxes around the source object and target location.

Limitations

This is an early preview release and may produce artifacts or inconsistencies in challenging cases, including:

—Complex backgrounds
—Large or overlapping objects
—Fine structures and textures
—Reflections and transparent objects
—Difficult lighting and perspective conditions
—Ambiguous source or target bounding boxes

Results can vary depending on the input image, object, bounding box placement, and target location.

License

Please refer to the license terms of the base model, Qwen-Image-2.1, and ensure compliance with its terms when using or redistributing this adapter.

Acknowledgements

This adapter was created by prithivMLmods and is built for use with Qwen-Image-2.1.