Overview

Computer vision and vision-language models on CLORE.AI GPUs.

Available Guides

Model	Use Case
LLaVA	Vision chat & QA
Florence-2	Multi-task vision
SAM2	Video segmentation
GroundingDINO	Zero-shot detection

Use Cases

• Image understanding - LLaVA, Florence-2

• Object detection - GroundingDINO, YOLO

• Segmentation - SAM2, Segment Anything

• Captioning - Florence-2, LLaVA

GPU Requirements

Model	Minimum VRAM
LLaVA 7B	8GB
Florence-2	8GB
SAM2	8GB
GroundingDINO	6GB

Related Guides

• Language Models

• Computer Vision