Instructions to use prithivMLmods/Qwen-Image-2.1-Natural-Exposure-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use prithivMLmods/Qwen-Image-2.1-Natural-Exposure-LoRA 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-Natural-Exposure-LoRA") 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-Natural-Exposure-LoRA
Qwen-Image-2.1-Natural-Exposure-LoRA is a LoRA adapter for Qwen-Image-2.1, designed to transform images with balanced, neutral exposure while preserving natural colors, details, lighting, and overall image consistency.
This is an experimental preview model. Results may vary depending on the input image, lighting conditions, and overall image composition.
Model Details
- Base Model: Qwen/Qwen-Image-2.1
- Adapter:
Qwen-Image-2.1-Natural-Exposure-LoRA - Model Type: LoRA / Adapter
- Model Status: Preview / Experimental
- Created by: prithivMLmods
Training Specifications
| Parameter | Configuration |
|---|---|
| Dataset | 38 pairs of high-quality images with manually adjusted exposure |
| Save Precision | BF16 |
| Learning Rate | 1e-4 |
| Optimizer | AdamW |
| Network Dimension (Rank) | 16 |
| Total Steps | 4000 |
| Trigger Prompt | Transform the image with balanced neutral exposure |
Download
Download the model files from the Files & versions tab:
Download Qwen-Image-2.1-Natural-Exposure-LoRA
Usage
Load the LoRA adapter with Qwen-Image-2.1 and provide an input image.
Use the trigger prompt:
Transform the image with balanced neutral exposure
For best results, use images with noticeable exposure variations or uneven lighting.
Limitations
This is an early preview release and may produce artifacts or inconsistencies in challenging cases, including:
- Extremely underexposed or overexposed images
- Complex lighting conditions
- High-contrast scenes
- Strong color casts
- Fine details and textures
- Images with unusual exposure or lighting conditions
Results can vary depending on the input image and its original lighting conditions.
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
- 129
Model tree for prithivMLmods/Qwen-Image-2.1-Natural-Exposure-LoRA
Base model
Qwen/Qwen-Image-2.1
