构建了2854对风格一致的图像变体数据集，用于评测生成模型的上下文一致性。
Moonworks Lunara Aesthetic II: An Image Variation Dataset
- 通过光照、天气等10余种变换保持图像身份稳定
- 在保留高美学评分的前提下实现强属性控制
- 适合评估生成模型的身份保持与编辑鲁棒性
我们推出Lunara Aesthetic II，一个公开可获取、伦理合规的图像数据集，旨在支持现代图像生成与编辑系统中上下文一致性的可控评估与学习。该数据集包含2,854对源自Moonworks原创艺术与摄影的锚点关联变体对，每对应用光照、天气、视角、场景构图、色彩色调或情绪等上下文变换，同时保持稳定的底层身份。该数据集将身份保持的上下文变体作为监督信号，并保留了Lunara原有的高美学评分。实验结果表明，该数据集具有高身份稳定性、强目标属性实现能力及优于大规模网络数据集的稳健美学表现。数据集采用Apache 2.0许可发布，可用于基准测试、微调及分析图像生成与图像到图像系统中的上下文泛化、身份保持与编辑鲁棒性，具备可解释的相对监督机制。数据集公开获取地址：https://huggingface.co/datasets/moonworks/lunara-aesthetic-image-variations。
原文摘要 · Abstract (English)
We introduce Lunara Aesthetic II, a publicly released, ethically sourced image dataset designed to support controlled evaluation and learning of contextual consistency in modern image generation and editing systems. The dataset comprises 2,854 anchor-linked variation pairs derived from original art and photographs created by Moonworks. Each variation pair applies contextual transformations, such as illumination, weather, viewpoint, scene composition, color tone, or mood; while preserving a stable underlying identity. Lunara Aesthetic II operationalizes identity-preserving contextual variation as a supervision signal while also retaining Lunara's signature high aesthetic scores. Results show high identity stability, strong target attribute realization, and a robust aesthetic profile that exceeds large-scale web datasets. Released under the Apache 2.0 license, Lunara Aesthetic II is intended for benchmarking, fine-tuning, and analysis of contextual generalization, identity preservation, and edit robustness in image generation and image-to-image systems with interpretable, relational supervision. The dataset is publicly available at: https://huggingface.co/datasets/moonworks/lunara-aesthetic-image-variations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。