$ loading_
Analyze local images in OpenCode using Google Gemini vision capabilities.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "vision" yet — see the docs or source repo.
Analyze this local app UI screenshot and summarize the layout, key components, and possible usability issues.
A structured description of the screenshot, including key UI elements and potential issues.
Inspect this local image and describe the main objects, visible text, and overall scene.
A summary of the image content with object recognition, text details, and scene description.
Analyze this local design mockup and list its visual hierarchy, color characteristics, and areas for improvement.
Visual analysis results for the mockup along with actionable improvement suggestions.
Developers or researchers can ask OpenCode to analyze local image content directly instead of describing it manually. This is useful for quickly extracting objects, text, or scene descriptions.
Designers or product managers can use it to inspect UI screenshots and mockups, getting quick analysis of structure and visual highlights. It helps with early reviews and communication.
It adds vision capabilities to OpenCode by using the Google Gemini API to analyze local images. The description says it supports PNG, JPG, WebP, GIF, HEIC, and SVG.
It is known to rely on the Google Gemini API for image analysis. For exact setup steps or API key configuration, see the source repository.
Based on the provided description, it supports local PNG, JPG, WebP, GIF, HEIC, and SVG images. For other formats, see the source repository.
Analyze images, extract text, and answer visual questions with LLM vision models.
Add screenshot analysis and visual Q&A to OpenCode via OpenAI-compatible vision endpoints.
Analyze screenshots, extract text, and compare visuals with image understanding.
Connect local vision models for image analysis, comparison, and OCR.
Analyze images with Gemini using flexible access methods and security controls.
Run local OCR and image analysis on macOS using Apple Vision.