展示HN:PaperBanana – 粘贴方法论文本,获取出版准备好的图表
我厌倦了在 PowerPoint 和 TikZ 中花费数小时绘制论文的方法论图表。因此,我创建了 PaperBanana——你只需粘贴你的方法部分文本,它会在大约 2-3 分钟内生成一幅适合发表的图表。
<p>其工作原理如下:</p>
1. 一个检索代理在一个经过精心策划的真实学术图表数据库中搜索,寻找结构相似的参考文献。
2. 一个规划代理读取你的文本,并生成详细的视觉描述(布局、组件、连接、分组)。
3. 一个风格代理在不改变内容的情况下美化视觉效果。
4. 然后进入一个迭代循环:可视化器生成图像,评论者评估图像并提出修改建议——这个过程重复 1-5 次(你可以选择)。
<p>关键的见解是,学术图表遵循一定的规范——变换器架构、生成对抗网络(GAN)管道、强化学习人类反馈(RLHF)框架都有可识别的视觉模式。通过首先检索相关参考,输出的结果更接近你实际会在论文中使用的内容,而不是通用的 AI 图像生成。</p>
<p>构建技术:Next.js + FastAPI + Celery,使用 Gemini 2.5 Flash 进行规划/评估,使用 Nanobanana Pro/Seedream 进行图像生成。</p>
<p>在这里试试:<a href="https://paperbanana.online" rel="nofollow">https://paperbanana.online</a></p>
<p>一些它处理得很好的示例:变换器架构、GAN 训练管道、RLHF 框架、多智能体系统、编码器-解码器架构。</p>
<p>已知的局限性:
- 最适用于计算机科学/人工智能方法论图表——未针对生物学、化学或一般科学插图进行优化。
- 生成图像中的文本渲染尚不完美——有时标签会稍微混乱。
- 精心策划的参考数据库仍然较小(13 个示例),扩展工作正在进行中。</p>
<p>希望能得到定期写论文的人的反馈。你最难处理的图表类型是什么?</p>
查看原文
I got tired of spending hours in PowerPoint and TikZ drawing methodology diagrams for my papers. So I built PaperBanana — you paste your Method section text, and it generates a publication-ready figure in about 2-3 minutes.<p>How it works under the hood:<p>1. A Retriever agent searches a curated database of real academic diagrams to find structurally similar references
2. A Planner agent reads your text and generates a detailed visual description (layout, components, connections, groupings)
3. A Stylist agent polishes the visual aesthetics without changing content
4. Then it enters an iterative loop: a Visualizer generates the image, and a Critic evaluates it and suggests revisions — this repeats 1-5 times (you choose)<p>The key insight is that academic diagrams follow conventions — Transformer architectures, GAN pipelines, RLHF frameworks all have recognizable visual patterns. By retrieving relevant references first, the output is much closer to what you'd actually put in a paper vs. generic AI image generation.<p>Built with: Next.js + FastAPI + Celery, using Gemini 2.5 Flash for planning/critique and Nanobanana Pro/Seedream for image generation.<p>Try it here: <a href="https://paperbanana.online" rel="nofollow">https://paperbanana.online</a><p>Some examples it handles well: Transformer architectures, GAN training pipelines, RLHF frameworks, multi-agent systems, encoder-decoder architectures.<p>Known limitations:
- Works best for CS/AI methodology diagrams — not optimized for biology, chemistry, or general scientific illustration
- Text rendering in generated images isn't perfect yet — sometimes labels get slightly garbled
- The curated reference database is still small (13 examples), expanding it is ongoing work<p>Would love feedback from anyone who writes papers regularly. What types of diagrams do you struggle with most?