google/medgemma-1.5-4b-it
Image-Text-to-Text β’ 4B β’ Updated β’ 167k β’ 616
Demo of the Collection of Qwen Image Edit LoRAs
Demo of the Qwen 3.5 Multimodal Model
Generate images from text prompts in seconds
Search and navigate electronic health records
Ask a question about the medical image
Simulated Pre-visit Intake Demo built using MedGemma
Real-time video captioning powered by FastVLM
Generate handβdrawn style diagram images from text
Expand and resize images with prompts
Elevating Ghibli-style AI art beyond ChatGPT's capabilities.