IFAdapter - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #react #typescript #llm #golang #android #rust #docker #macos #nodejs #awesome-list #security #openai

IFAdapter

(★ 62)

[ICCV2025] Official implementation of "IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation".

File Explorer

Download Latest Version (.zip)

- compare.png
- fig1.png
- lora.png
- pipeline.png
- 1.json
- 1_lora.json
- 2.json
- 2_lora.json
- 3.json
- 3_lora.json
- lora.json
- - __init__.cpython-39.pyc
  - attention_processor.cpython-39.pyc
  - if_adapter.cpython-39.pyc
  - resampler.cpython-39.pyc
  - sdxl_pipeline.cpython-39.pyc
- __init__.py
- attention_processor.py
- if_adapter.py
- resampler.py
- sdxl_pipeline.py
__init__.py
arial.ttf
ifa_dataset.py
infer.py
infer.txt
infer_lora.txt
infer_loras.py
Rainbow-Party-2.ttf
README.md
requirements.txt

# Installation Guide

1. Get the code

git clone https://github.com/WUyinwei-hah/IFAdapter

Downloads the entire project code from GitHub to your computer.

cd IFAdapter

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<div align="center">

<h1>IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation</h1>

<div>
Yinwei Wu<sup>1,2</sup>&emsp;Xianpan Zhou<sup>1</sup>&emsp;Bing Ma<sup>1</sup>&emsp;Xuefeng Su<sup>1</sup>&emsp;Kai Ma<sup>1</sup>&emsp;Xinchao Wang<sup>2</sup><sup>&dagger;</sup>
</div>
<div>
    <sup>1</sup>Tencent PGC&emsp;
    <sup>2</sup>National University of Singapore&emsp;
    <sup>&dagger;</sup>corresponding author 
</div>

</div>

---
## Overview
![overall_structure](https://raw.githubusercontent.com/WUyinwei-hah/IFAdapter/main/assets/fig1.png)

We introduce the **I**nstance **F**eature **Adapter**(IFAdapter) to to exert fine-grained control over the generation of multiple instances.

## Features
The IFAdapter is readily integrated with various community models and LoRAs!
![loras](https://raw.githubusercontent.com/WUyinwei-hah/IFAdapter/main/assets/lora.png)
We show the results of IFAdapter in combination with [PixelArt](https://civitai.com/models/120096/pixel-art-xl), [Lelo-Lego](https://civitai.com/models/92444/lelo-lego-lora-for-xl-and-sd15), [Claymation](https://huggingface.co/DoctorDiffusion/doctor-diffusion-s-claymation-style-lora), and [Bluepencil](https://civitai.com/models/119012/bluepencil-xl). We express our gratitude for these great work contributed by these communities!

## Quick Start

Install the required dependencies
```bash
git clone https://github.com/WUyinwei-hah/IFAdapter.git

cd IFAdapter

pip install -r requirements.txt
```

## Generation

1.
Use the original SDXL for generation
```python
python3 infer.py
```

2.
Use LORAs for generation
```python
python3 infer_loras.py
```
---

## Citation
```
@article{wu2024ifadapter,
  title={Ifadapter: Instance feature control for grounded text-to-image generation},
  author={Wu, Yinwei and Zhou, Xianpan and Ma, Bing and Su, Xuefeng and Ma, Kai and Wang, Xinchao},
  journal={arXiv preprint arXiv:2409.08240},
  year={2024}
}
```