README.md

---
license: apache-2.0
---
# AttriCtrl Numerical Image Generation Control Model

## Introduction

AttriCtrl enables fine-grained control of numerical image attributes during image generation.

For more details, please refer to our paper: [AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models](https://arxiv.org/abs/2508.02151)

## Result Demonstration

### Brightness

|scale = 0.1|scale = 0.3|scale = 0.5|scale = 0.7|scale = 0.9|
|-|-|-|-|-|
|![](./assets/brightness/value_control_0.1.jpg)|![](./assets/brightness/value_control_0.3.jpg)|![](./assets/brightness/value_control_0.5.jpg)|![](./assets/brightness/value_control_0.7.jpg)|![](./assets/brightness/value_control_0.9.jpg)|

### Detail

|scale = 0.1|scale = 0.3|scale = 0.5|scale = 0.7|scale = 0.9|
|-|-|-|-|-|
|![](./assets/detail/value_control_0.1.jpg)|![](./assets/detail/value_control_0.3.jpg)|![](./assets/detail/value_control_0.5.jpg)|![](./assets/detail/value_control_0.7.jpg)|![](./assets/detail/value_control_0.9.jpg)|

### Realism

|scale = 0.1|scale = 0.3|scale = 0.5|scale = 0.7|scale = 0.9|
|-|-|-|-|-|
|![](./assets/realism/value_control_0.1.jpg)|![](./assets/realism/value_control_0.3.jpg)|![](./assets/realism/value_control_0.5.jpg)|![](./assets/realism/value_control_0.7.jpg)|![](./assets/realism/value_control_0.9.jpg)|

## Inference Code

```shell
git clone https://github.com/modelscope/DiffSynth-Studio.git  
cd DiffSynth-Studio
pip install -e .
```

```python
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
```

```python
pipe = FluxImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
        ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/detail.safetensors")
    ],
)

for i in [0.1, 0.3, 0.5, 0.7, 0.9]:
    image = pipe(prompt="a cat on the beach", seed=2, value_controller_inputs=[i])
    image.save(f"value_control_{i}.jpg")
```