LightX AI Poster Generator vs PosterGen

LightX AI Poster Generator has no write-up on Specifiction yet; its figures are above.

PosterGen generates academic posters from research paper PDFs, using a multi-agent language-model workflow to extract content, plan a narrative, arrange the layout, and apply styling. Its Parser Agent structures paper content, while the Curator Agent plans organization and visual placement. Layout and Balancer agents calculate spacing and column use, with the Balancer addressing overflow. Styling includes colors drawn from an affiliation logo, professional font choices, and keyword highlighting. Users can adjust layout, typography, color generation, visual asset sizing, and content optimization through configuration. A local web interface accepts a paper PDF and logos, lets users configure models and poster dimensions, and generates a PNG plus an editable PowerPoint file. Documented width-to-height ratios run from 1.4 to 2, and custom dimensions are supported. The project lists Windows, Linux, and macOS, but setup requires Python 3.11 and LibreOffice; the web interface also needs Node.js and configured API keys. Setup documents OpenAI, Anthropic, and Zhipu keys, with configurable service base URLs including Google. PosterGen is free and MIT-licensed; the license provides the software without warranty.