🤖 Model 🖼️ → 📝

salesforce/blip
Caption images from a single input image. Answer visual questions about the image and evaluate image-text matching by ch...
Found 2 models (showing 1-2)
Caption images from a single input image. Answer visual questions about the image and evaluate image-text matching by ch...
Perform zero-shot image classification by scoring an input image against multiple text labels. Provide one image and a p...