Multimodal Language Model
Search and detect objects in images using text queries
Evaluate anime aesthetic score
Complete depth for images using sparse depth maps
Generate 3D depth map visualization from an image
Enhance faces in old or AI-generated photos
Browse Danbooru images with filters and sorting
Search for medical images using natural language queries
Tag images with NSFW labels
Visualize attention maps for images using selected models
Gaze Target Estimation
Search images by text or upload
Restore and enhance images
Watermark detection
Train LoRA with ease
Detect budgerigar gender based on cere color
Detect ASL letters in images
Find similar images using tags and images
Swap faces in images
Identify objects in images using ResNet