Instructions to use prithivMLmods/Qwen-Image-2.1-Object-Mover-Bbox-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prithivMLmods/Qwen-Image-2.1-Object-Mover-Bbox-turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2.1", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("prithivMLmods/Qwen-Image-2.1-Object-Mover-Bbox-turbo") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Qwen-Image-2.1-Object-Mover-Bbox-turbo
Qwen-Image-2.1-Object-Mover-Bbox-turbo is a Turbo-optimized LoRA adapter for Qwen-Image-2.1, designed for object movement using bounding box guidance. The adapter moves an object highlighted by a red bounding box to the location indicated by another red bounding box while attempting to preserve the object's appearance, surrounding textures, lighting, shadows, perspective, and overall image consistency.
The adapter is optimized for fast Turbo inference and can also be used with standard inference workflows.
This is an experimental model. Results may vary depending on the input 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-turbo - Model Type: LoRA / Adapter
- Model Status: Experimental
- Inference: Turbo / Standard
- Created by: prithivMLmods
Training Specifications
| Parameter | Configuration |
|---|---|
| Dataset | 45 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 | 4000 |
| 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-turbo
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:
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 both the source object and target location.
Inference
This adapter is optimized for fast Turbo inference and can also be used with standard inference workflows.
For Turbo inference, follow the recommended inference configuration for Qwen-Image-2.1 and apply the adapter using the appropriate Turbo workflow.
Limitations
This is an experimental 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 or poorly positioned bounding boxes
- Significant changes in object scale or perspective
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.
- Downloads last month
- 89
Model tree for prithivMLmods/Qwen-Image-2.1-Object-Mover-Bbox-turbo
Base model
Qwen/Qwen-Image-2.1
