让AI根据韩语日记生成有情绪色彩的儿童手绘风图像
Emotion-Aware Image Generation from Korean Diary Text via LLM-based Prompt Translation and LoRA Fine-Tuning
- 用Qwen3识别日记中的隐含情绪，再用带情绪词的LoRA微调扩散模型
- 在儿童手绘风格数据集上微调，生成图像情绪匹配度提升明显
- 适合做情感计算与创意生成交叉研究的学者参考
文本到图像模型难以有效捕捉日记等文本中的情感，因其主要关注视觉对象而非上下文情感理解。本文提出一种情绪感知的图文生成流程，可从简短韩语日记生成儿童手绘风格图像。该流程采用Qwen3-8B识别日记中隐含情感，并基于情绪触发词对Stable Diffusion 3.5 Medium进行LoRA微调，训练数据为儿童绘画图像。实验还分析了情绪触发词对生成图像的影响，并讨论了CLIP Score作为情绪感知图像生成评估指标的局限性。
原文摘要 · Abstract (English)
T2I models cannot effectively capture sentiment from various types of text, including diaries, as they primarily focus on visual object-related patterns rather than contextual emotional understanding. This paper proposes an emotion-aware text-to-image pipeline that generates children's hand drawing style images from short Korean diary entries. The proposed pipeline employs Qwen3-8B for recognising implicit sentiment from short diaries, and Stable Diffusion 3.5 Medium fine-tuned with LoRA on children's drawing images with emotion-based trigger words for image generation. Additionally, this paper presents experiments examining the effect of emotion trigger words on generated images and discusses the limitations of CLIP Score as an evaluation metric for emotion-aware image generation.
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。