README.md

---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen-Image-Edit-2511
pipeline_tag: image-to-image
library_name: diffusers
tags:
- lora
- flat-log
- true-color
---

![1](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/nGb29B9wabkxXEO5k74fH.png)

# **QIE-2511-FlatLog2TrueColor**

> **QIE-2511-FlatLog2TrueColor** is an adapter LoRA developed for Qwen’s **Qwen-Image-Edit-2511** image-to-image model, designed to transform flat log images into true, natural colors. The model restores contrast, saturation, and tonal balance while preserving the original identity, composition, textures, and geometry. It enables accurate color recovery with smooth highlight roll-off, well-controlled shadows, and artifact-free results.

## **Quick Start with Diffusers**

> Compatible with versions **2509** and **2511**.

```bash
pip install -U diffusers transformers accelerate
```

```python
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-Edit-2511",
    dtype=torch.bfloat16,
    device_map="cuda"
)

pipe.load_lora_weights("prithivMLmods/QIE-2511-FlatLog2TrueColor")

prompt = "Transform a flat log image into true colors"

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]
```

**Trained on [ModelScope.cn](https://modelscope.cn)**

## **Trigger Prompt**

Use the following prompt to activate the flat-log to true-color behavior:

```
Transform a flat log image into true colors
```

## **Download Model**

You can download the model files from the **Files & versions** tab:
[Download](https://huggingface.co/prithivMLmods/QIE-2511-FlatLog2TrueColor/tree/main)