README.md

---
base_model:
- black-forest-labs/FLUX.1-Fill-dev
pipeline_tag: text-to-image
library_name: transformers
tags:
- art
---

# Calligrapher: Freestyle Text Image Customization

<div align="center">
  <img src="./assets/teaser.jpg" width="850px" alt="Calligrapher Teaser">
</div>

<div align="center">
  <h3>📄 <a href="https://ezioby.github.io/Calligrapher/">Project Page</a> | 📦 <a href="https://github.com/Calligrapher2025/Calligrapher">Code</a> | 🎥 <a href="https://youtu.be/FLSPphkylQE">Video</a> | 🤗 <a href="https://huggingface.co/spaces/Calligrapher2025/Calligrapher">HF_Demo</a> </h3>
</div>

## 🎯 Overview

**Calligrapher** is a novel diffusion-based framework that innovatively integrates advanced text customization with artistic typography for digital calligraphy and design applications. Our framework supports text customization under various settings including self-reference, cross-reference, and non-text reference customization.

## ✨ Key Features

- **🎨 Freestyle Text Customization**: Generate text with diverse stylized images and text prompts
- **🔄 Various Reference Modes**: Support for self-reference, cross-reference, and non-text reference customization
- **🚀 High-Quality Results**: Photorealistic text image customization with consistent typography
- **🌐 Multi-Language Support**: Style-centric text customization across diverse languages (see <a href="https://github.com/Calligrapher2025/Calligrapher/issues/1">this issue</a>)
<div align="center">
  <img src="./assets/multilingual_samples.png" width="900px" alt="Multilingual Samples">
</div>
## 📦 Repository Contents

This Hugging Face repository contains:

- **`calligrapher.bin`**: Pre-trained Calligrapher model weights.
- **`Calligrapher_bench_testing.zip`**: Comprehensive test dataset with examples for both self-reference and cross-reference customization scenarios with additional reference images for testing, omitting a small portion of samples due to IP concerns.



## 🛠️ Quick Start

### Installation

We provide two ways to set up the environment (requiring Python 3.10 + PyTorch 2.5.0 + CUDA):

#### Using pip
```bash
# Clone the repository
git clone https://github.com/Calligrapher2025/Calligrapher.git
cd Calligrapher

# Install dependencies
pip install -r requirements.txt
```

#### Using Conda
```bash
# Clone the repository
git clone https://github.com/Calligrapher2025/Calligrapher.git
cd Calligrapher

# Create and activate conda environment
conda env create -f env.yml
conda activate calligrapher
```

### Download Models & Testing Data

```python
from huggingface_hub import snapshot_download

# Download Calligrapher model and test data
snapshot_download("Calligrapher2025/Calligrapher")
# Download required base models (granted access needed for FLUX.1-Fill)
snapshot_download("black-forest-labs/FLUX.1-Fill-dev", token="your_token")
snapshot_download("google/siglip-so400m-patch14-384")
```

### Configuration

Before running the models, you need to configure the paths in `path_dict.json`:

```json
{
  "data_dir": "path/to/Calligrapher_bench_testing",
  "cli_save_dir": "path/to/cli_results",
  "gradio_save_dir": "path/to/gradio_results",
  "gradio_temp_dir": "path/to/gradio_tmp",
  "base_model_path": "path/to/FLUX.1-Fill-dev",
  "image_encoder_path": "path/to/siglip-so400m-patch14-384",
  "calligrapher_path": "path/to/calligrapher.bin"
}
```

Configuration parameters:
- `data_dir`: Path to store the test dataset
- `cli_save_dir`: Path to save results from command-line interface experiments
- `gradio_save_dir`: Path to save results from Gradio interface experiments
- `gradio_temp_dir`: Path to save Gradio temporary files
- `base_model_path`: Path to the base model FLUX.1-Fill-dev
- `image_encoder_path`: Path to the SigLIP image encoder model
- `calligrapher_path`: Path to the Calligrapher model weights

### Run Gradio Demo

```bash
# Basic Gradio demo
python gradio_demo.py

# PLEASE consider trying examples here first - demo with custom mask upload (recommended for first-time users)
# This version includes pre-configured examples and is RECOMMENDED for users to first understand how to use the model
python gradio_demo_upload_mask.py

```

Below is a preview of the Gradio demo interfaces:

<div align="center">
  <img src="./assets/gradio_preview.png" width="900px" alt="Gradio Demo Preview">
</div>

We also provide a gradio demo enabling multilingual freestyle text customization such as Chinese, which is supported by [TextFLUX](https://github.com/yyyyyxie/textflux). To use this gradio demo, first download [TextFLUX weights](https://huggingface.co/yyyyyxie/textflux-lora/blob/main/pytorch_lora_weights.safetensors) and configure the "textflux_path" entry in "path_dict.json". Then download [the font resource](https://github.com/yyyyyxie/textflux/blob/main/resource/font/Arial-Unicode-Regular.ttf) to "./resources/" and run:
```bash
python gradio_demo_multilingual.py
```

**✨User Tips:**

1. **Speed vs Quality Trade-off.** Use fewer steps (e.g., 10-step which takes ~4s/image on a single A6000 GPU) for faster generation, but quality may be lower.

2. **Inpaint Position Freedom.** Inpainting positions are flexible - they don't necessarily need to match the original text locations in the input image.

3. **Iterative Editing.** Drag outputs from the gallery to the Image Editing Panel (clean the Editing Panel first) for quick refinements.

4. **Mask Optimization.** Adjust mask size/aspect ratio to match your desired content. The model tends to fill the masks, and harmonizes the generation with background in terms of color and lighting.

5. **Reference Image Tip.** White-background references improve style consistency - the encoder also considers background context of the given reference image.

6. **Resolution Balance.** Very high-resolution generation sometimes triggers spelling errors. 512/768px are recommended considering the model is trained under the resolution of 512.

## 🎨 Command Line Usage Examples

### Self-reference Customization
```bash
python infer_calligrapher_self_custom.py
```

### Cross-reference Customization
```bash
python infer_calligrapher_cross_custom.py
```

**Note:** Image result files starting with "result" are the customization outputs, while files starting with "vis_result" are concatenated results showing the source image, reference image, and model output together.

## 📊 Framework

<div align="center">
  <img src="./assets/framework.jpg" width="900px" alt="Calligrapher Framework">
</div>

Our framework integrates localized style injection and diffusion-based learning, featuring:
- **Self-distillation mechanism** for automatic typography benchmark construction.
- **Localized style injection** via trainable style encoder.
- **In-context generation** for enhanced style alignment.

## 🎭 Results Gallery

<div align="center">
  <img src="./assets/application.jpg" width="900px" alt="Calligrapher Applications">
</div>