prompt_description_stable_diffusion_1k
收藏魔搭社区2025-07-24 更新2025-07-26 收录
下载链接:
https://modelscope.cn/datasets/gokaygokay/prompt_description_stable_diffusion_1k
下载链接
链接失效反馈官方服务:
资源简介:
# The Synthetic Description from Prompts Dataset
This dataset is created using the Phi 2 3B Q4_K_S quantized model, using 1k random samples from training set of a base dataset of about 80,000 prompts from the Stable Diffusion dataset on Lexica.art. This dataset is designed to explore the capabilities of language models in generating creative and expanded descriptions from concise prompts.
### Source Data
https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts
# 基于提示词的合成描述数据集
本数据集依托Phi 2 3B Q4_K_S量化模型构建,从Lexica.art平台的Stable Diffusion基础数据集(包含约80000条提示词)的训练集中随机抽取1000条样本生成。本数据集旨在探索大语言模型(Large Language Model)从简洁提示词生成兼具创造性与拓展性的描述文本的能力。
### 源数据
https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts
提供机构:
maas
创建时间:
2025-07-22



