multimodal-blip-2
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
[MultimodalVision-LanguageImageCaptioning
Orchestra Research
33,1943,891
multimodal-segment-anything
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
[MultimodalImageSegmentationComputer
Orchestra Research
33,1943,891
segment-anything-model
SAM: zero-shot image segmentation via points, boxes, masks.
[MultimodalImageSegmentationComputer
delorenj
176
segment-anything-model
SAM: zero-shot image segmentation via points, boxes, masks.
[MultimodalImageSegmentationComputer
poorrican
0
segment-anything-model
SAM: zero-shot image segmentation via points, boxes, masks.
[MultimodalImageSegmentationComputer
PoorRican
0