Ready to use and editable Computer Vision algorithms from your favorite frameworks.
113 items found
Items per page
Face inpainting using Segformer for segmentation and RealVisXL for inpainting.
Inference for MMOCR from MMLAB KIE models
Stable Cascade is a diffusion model trained to generate images given a text prompt.
YOLO-World is a real-time zero-shot object detection modelthat leverages the power of open-vocabulary learning to recognize and localize a wide range of objects in images.
Depth Anything is a highly practical solution for robust monocular depth estimation
Object detection with YOLOv9 models
Train YOLOv9 models
Kandinsky 2.2 inpainting diffusion model.
Kandinsky 2.2 image-to-image diffusion model.
Kandinsky 2.2 image mixing diffusion model.