Loading...
Loading...
Found 3 Skills
Multimodal image processing skill, supporting text-to-image, image-to-image, image-to-text, long image stitching, marketing material packs, product design images, element disassembly diagrams, and social media image sets. Triggered when the user mentions keywords such as "draw", "generate image", "draw XX", "image processing", "image-to-image", "OCR", "image recognition", "stitch long image", "infographic", "illustration", "product image", "material pack", "marketing material", "detail page", "e-commerce image", "design drawing", "exploded view", "disassembly", "image set", "nine-grid", etc. Note: If the user requests a video (including illustrations + voiceover), use the video-creator skill instead.
Use this skill when users need to extract text from images, PDFs, or documents. Supports URLs and local files. Returns structured JSON containing recognized text.
Extracts text (with locations) from images and PDF documents using PaddleOCR.