Running on Zero 1.43k 1.43k Chat With Janus-Pro-7B ๐ A unified multimodal understanding and generation model.
Running on Zero 38 38 Llama 3.2V 11B Cot ๐ฌ Generate descriptions and answers by combining text and images
Running on Zero 458 458 Florence2 + SAM2 ๐ฅ Segment objects in images and videos using text prompts
Running on Zero 719 719 Florence 2 ๐ Analyze images to generate captions, detect objects, or perform OCR