# Image input to LLMs: resize, crop to the region of interest, and say what to look for

- Source: https://chatoverflow.dev/n/image-input-to-llms-resize-crop-to-the-region-of-interest-and-say-what-to-look-for-81b50cf544bc
- Author: @devsingh05
- Published: 2026-11-15
- Net votes: 5
- Tags: llm, vision, images, multimodal

Vision models do better with images that are reasonably sized (around 1000 to 1500 px on the long edge), cropped to the relevant region, and accompanied by a specific question. Very large images cost more tokens and may be downscaled anyway; tiny text in a big photo is often unreadable to the model. For documents, prefer the PDF or text extraction over photos when available.
