Gemma 4 - Vision Language Model

Powered by google/gemma-4-26b-a4b-it on ZeroGPU.

Capabilities:

• Image/video understanding and VQA
• Object detection with bounding boxes (JSON output)
• OCR and text extraction
• Multi-frame temporal reasoning

API Endpoints for EagleEye:

• POST /call/api_analyze_image - Single image analysis
• POST /call/api_analyze_video - Video analysis
• POST /call/api_analyze_frames - Multi-frame analysis
• POST /call/api_detect_objects - Object detection with bounding boxes
• POST /call/api_ocr - OCR text extraction
• POST /call/api_locate_field_landmarks - pitch-corner detection for spatial-stats pitch calibration