Synthbuster: Towards Detection of Diffusion Model Generated Images

Dataset described in the paper "Synthbuster: Towards Detection of Diffusion Model Generated Images" (Quentin Bammey, 2023, Open Journal of Signal Processing)
This dataset contains synthetic, AI-generated images from 9 different models:

DALL·E 2
DALL·E 3
Adobe Firefly
Midjourney v5
Stable Diffusion 1.3
Stable Diffusion 1.4
Stable Diffusion 2
Stable Diffusion XL
Glide

1000 images were generated per model. The images are loosely based on raise-1k images (Dang-Nguyen, Duc-Tien, et al. "Raise: A raw images dataset for digital image forensics." Proceedings of the 6th ACM multimedia systems conference. 2015.). For each image of the raise-1k dataset, a description was generated using the Midjourney /describe function and CLIP interrogator (https://github.com/pharmapsychotic/clip-interrogator/). Each of these prompts was manually edited to produce results as photorealistic as possible and remove living persons and artists names.

In addition to this, parameters were randomly selected within reasonable values for methods requiring so.
The prompts and parameters used for each method can be found in the `prompts.csv` file.

This dataset can be used to evaluate AI-generated image detection methods. We recommend matching the generated images with the real Raise-1k images, to evaluate whether the methods can distinguish the two of them. Raise-1k images are not included in the dataset, they can be downloaded separately at (http://loki.disi.unitn.it/RAISE/download.html).

None of the images suffered degradations such as JPEG compression or resampling, which leaves room to add your own degradations to test robustness to various transformation in a controlled manner.

本数据集源自论文《Synthbuster: 面向扩散模型生成图像检测》（Quentin Bammey，2023，《开放信号处理期刊》(Open Journal of Signal Processing)）。
本数据集包含来自9种不同模型的AI合成生成图像，分别为：DALL·E 2、DALL·E 3、Adobe Firefly、Midjourney v5、Stable Diffusion 1.3、Stable Diffusion 1.4、Stable Diffusion 2、Stable Diffusion XL、Glide。
每个模型均生成1000张图像。这些图像大体以RAISE-1k数据集（raise-1k）图像为原型创作，相关原始研究为：Dang-Nguyen, Duc-Tien 等人发表的《RAISE：用于数字图像取证的原始图像数据集》，收录于第6届ACM多媒体系统大会论文集，2015年。
针对RAISE-1k数据集中的每张图像，我们使用Midjourney的/describe功能与CLIP图像问询器（CLIP interrogator，https://github.com/pharmapsychotic/clip-interrogator/）生成图像描述提示词。随后对所有生成的提示词进行人工编辑，以尽可能生成贴近真实摄影的图像效果，并移除其中涉及的活体人物与艺术家姓名。
此外，对于需要配置参数的生成方法，我们在合理范围内随机选取参数值。各生成方法所使用的提示词与参数可在`prompts.csv`文件中获取。
本数据集可用于评估AI生成图像检测方法。我们建议将生成的合成图像与真实RAISE-1k图像进行匹配测试，以验证检测方法能否区分二者。需注意，RAISE-1k原始图像并未包含在本数据集中，用户可通过链接 http://loki.disi.unitn.it/RAISE/download.html 单独下载。
本数据集所有图像均未经过JPEG压缩、重采样等图像降级处理，因此可由使用者自行添加各类图像变换操作，以可控方式测试检测方法的鲁棒性。