AesExpert

Let MLLM perceive image aesthetics like humans. Try it now!

If you like this work, please give us a star ⭐ on GitHub.

Introduction

The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerbates this dilemma, resulting in MLLMs falling short of aesthetics perception capabilities. To address the above challenge, we first introduce a comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset, which serves as the footstone for building multi-modality aesthetics foundation models. Specifically, to align MLLMs with human aesthetics perception, we construct a corpus-rich aesthetic critique database with 21,904 diverse-sourced images and 88K human natural language feedbacks, which are collected via progressive questions, ranging from coarse-grained aesthetic grades to fine-grained aesthetic descriptions. To ensure that MLLMs can handle diverse queries, we further prompt GPT to refine the aesthetic critiques and assemble the large-scale aesthetic instruction tuning dataset, i.e. AesMMIT, which consists of 409K multi-typed instructions to activate stronger aesthetic capabilities. Based on the AesMMIT database, we fine-tune the open-sourced general foundation models, achieving multi-modality Aesthetic Expert models, dubbed AesExpert. Extensive experiments demonstrate that the proposed AesExpert models deliver significantly better aesthetic perception performances than the state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision.

News

• [2024/07/20] Welcome to our Project Page! 🔥🔥🔥
• [2024/07/16] We have released AesExpert (LLaVA-v1.5-7b) on BaiduYun and HuggingFace! Check it out!🤗🤗🤗

Quick Start

LLaVA-v1.5

Install LLaVA.

git clone https://github.com/haotian-liu/LLaVA.git
cd LLaVA
pip install -e .

Simple Interactive Demos.

See the codes and scripts below.

Example Code (Single Query)

from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model
model_path = "qyuan/AesMMIT_LLaVA_v1.5_7b_240325" 
prompt = "Describe the aesthetic experience of this image in detail."
image_file = "figs/demo1.jpg"
args = type('Args', (), {
    "model_path": model_path,
    "model_base": None,
    "model_name": get_model_name_from_path(model_path),
    "query": prompt,
    "conv_mode": None,
    "image_file": image_file,
    "sep": ",",
})()
eval_model(args)

Acknowledgement

We thank Teo Wu and Zicheng Zhang for their awesome works Q-Future.

Citation

If you find our work interesting, please feel free to cite our paper:

@article{AesExpert,
    title={AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception},
    author={Yipo Huang and Xiangfei Sheng and Zhichao Yang and Quan Yuan and Zhichao Duan and Pengfei Chen and Leida Li and Weisi Lin and Guangming Shi},
   journal={arXiv:2404.09624},
    year={2024},
}