paperbanana

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

Scientific figure workbench with independent VLM/image connections, Chinese UI, and unified size controls.

PaperBanana-AIMSLab是一个面向科研写作场景的AI学术配图助手，基于开源项目PaperBanana优化而来。它可以根据论文方法章节、图注或图表意图自动生成高质量学术配图，并支持多 Agent 规划、风格优化、图像生成、评审迭代和图片精修。项目针对国内使用环境增强了多 API 通道自动切换能力，支持 AIPAIBOX、Google Gemini、OpenAI 与兼容网关，并新增gpt-image-2图像生成与image-to-image精修支持。

AI agent for civil engineering research papers — 15 journals, 18 utilities, 4 templates, CLI + Web UI + Docker, PaperBanana diagrams, 245 tests. v1.0.0 released.

🍌 OpenClaw skill for generating publication-quality academic diagrams and plots from text using PaperBanana

开源科研图示工作台：Web、微信小程序、Tuyan Benchmark、Agent Skill 与匿名只读 MCP

跨 Agent 科研图示 Skill：FigureSpec、本地检索、生成、评审、精修与可复现输出

PaperBananaFX is a JavaFX desktop orchestration demo for a real-time AI workflow. It targets a specific bottleneck in the "AI scientist" workflow: converting method text and figure captions into publication-ready illustrations with semantic fidelity to the method and stylistic conformity to modern research-paper aesthetics.

匿名只读科研图示 MCP：版本化模板、规则、Schema 与工作流知识