@maqibin: AI-generated image-text posts are finally editable. Previously, when using AI to generate images, the biggest issue was: while they looked great, the text and layout were very difficult to modify afterwards. So I created a small tool called 'Paper Workshop'—input a piece of content, and it can generate a set of Xiaohongshu image-text posts, WeChat Moments long images, document resumes, and other cards. Moreover, the text, images, stickers, paper texture…
Summary
This article introduces 'Paper Workshop,' a small tool that allows editing AI-generated image-text posts, suitable for creating Xiaohongshu image-text posts, knowledge cards, and more. It demonstrates the complete workflow through a video.
Similar Articles
@mnmn94253156337: Let AI make a PPT for you, and it gives you a bunch of divs and a randomly laid out layout. Click to open, and it looks uglier than what you would have done yourself. What's more annoying is Excel—formulas are written incorrectly, formatting is all over the place, and after generation, you have to manually fix everything from start to finish. You might as well do it yourself. MiniMax open-sourced these four doc…
MiniMax open-sourced four AI document generation skills (PPT, PDF, Excel, Word), usable without an API key, aiming to solve issues like messy formatting and formula errors in AI-generated documents.
@zstmfhy: Just tried the gimi-illustration-skill open-sourced by Teacher Xiaomi, here's the bottom line: This thing is really practical. Throw an article in, AI automatically analyzes the structure, extracts key points, and generates hand-drawn illustrations. Consistent style, not templated. Supports custom IP character, create your own visual identity. Image size adjustable…
Teacher Xiaomi's open-source gimi-illustration-skill, input article content to automatically generate consistent hand-drawn illustrations, supports custom IP characters and multiple sizes, suitable for reports, guides, tutorials, etc., hosted on GitHub.
@vintcessun: Tonight I discovered a project with a novel approach: using GPT to generate luxurious image-format PPTs, then 'decompiling' them back into editable PPTX. Previously, AI-generated PPTs either stacked templates or only exported images. This one directly follows the 'generate image → parse → assemble' path. The core idea is to decompose the PPT image into four layers: background, frame, icons, and text, then reconstruct by coord...
An open-source project named GordenSuperPPTSkills uses GPT to generate luxurious image-format PPTs, then 'decompiles' them into fully editable PPTX files, solving the pain point of AI-generated content being non-editable. The project is split into three independent skills, supporting either just image generation or just image-to-editable conversion, suitable for Codex environment.
@Xudong07452910: Driven crazy by drawing figures for papers, revising till dawn? The open-source tool PaperBanana helps you generate figures with just one sentence: • Drop in the methodology text/PDF + a caption • Multi-Agent auto-pipeline: Plan → Stylize → Generate → Self-critic → Redraw • …
PaperBanana is an open-source tool that uses a multi-agent pipeline to automatically generate high-quality academic illustrations from paper PDFs and user descriptions. It supports multiple AI providers such as GPT-Image and Gemini, and provides CLI, Python API, and a web interface.
@op7418: https://x.com/op7418/status/2074728162018152817
The user released an open-source AI illustration skill called guizang-material-illustration, based on GPT-Image 2.0 and Codex Agent, which can generate 3D material explanation diagrams with Chinese labels, suitable for articles, weekly reports, PPTs, etc.