Captioning, segmentation, and preprocessing models for visual analysis.
Vision-language model for image understanding and captioning
Instruction-tuned vision-language model for image and text understanding
Instruction-tuned multimodal vision-language model
Lightweight face mask generation for realistic images
Lightweight hand mask generation for realistic images
Higher-accuracy face mask generation for realistic images
Content-shuffle preprocessor for color and texture transfer with looser spatial control
Tile-based preprocessor for detail reconstruction, enhancement, and local consistency
Soft-edge preprocessor for gentler contour guidance than hard Canny boundaries