NimaChu

You can extract text from images via automatic Tesseract or PaddleOCR selection, convert prompts into deterministic SVG assets exported as PNG, and produce complete Xiaohongshu image-and-text posts including research, fact checking, copy, pagination, storyboards, covers, and quality review.

Content creators and marketers producing 小红书图文, knowledge cards, comic-style explainers, or article-to-image series. It suits users who need per-page image prompts, a 3:4 cover, 9:16 content pages, and revisions to an existing Xiaohongshu series.

It prefers an available image-generation model for page visuals. When no image-generation tool is available, it falls back to the bundled fully local SVG-to-PNG renderer. SVG text patches are applied only after the user explicitly reports incorrect or unreadable text.

super-ocr requires Tesseract or PaddleOCR for text extraction. xhs-imagen works best with an image-generation model but includes a local SVG-to-PNG renderer as fallback. free-imagegen runs locally to export PNG from SVG without external services.

Yes. The skill includes research and fact checking as built-in stages before writing post copy, followed by pagination, storyboard creation, image generation, and a final quality review of the complete Xiaohongshu post set.