ebixhaferaj/handwriting-signatures-dataset
收藏资源简介:
一个包含手写签名及文本提示的数据集,专为扩散模型的LoRA微调设计,用于生成逼真的个人签名。该数据集经过预处理,适用于签名验证和文本到图像任务。处理步骤包括标注、使用OpenCV进行预处理(清洁、裁剪、居中、调整大小至256×256)和手动过滤低质量样本。数据集结构包含.png格式的签名图像和metadata.jsonl注释文件。每个样本包含签名图像和描述签名的文本提示。数据集基于CC-BY-NC-4.0许可证,仅限非商业用途。
A dataset of handwritten signatures with text prompts, designed for LoRA fine-tuning of diffusion models to generate realistic personal signatures. This dataset contains preprocessed handwritten signatures designed for signature verification and LoRA fine-tuning of diffusion models (e.g., Stable Diffusion) for text-to-image tasks. Processing steps include labeling, preprocessing with OpenCV (cleaning, cropping, centering, resizing to 256×256), and manual filtering of low-quality samples. The dataset structure includes .png files for signature images and metadata.jsonl for annotations. Each sample contains an image and a text prompt describing the signature. The dataset is licensed under CC-BY-NC-4.0 for non-commercial use only.




