Models/Collections/Automate visual understanding

Automate visual understanding

Captioning, segmentation, and preprocessing models for visual analysis.

Captioning

View all

Vision-language model for image understanding and captioning

$0.0013/ requestDefault
Run

Instruction-tuned vision-language model for image and text understanding

$0.0013/ requestDefault
Run

Instruction-tuned multimodal vision-language model

$0.0013/ requestDefault
Run

Masking

View all

Lightweight face mask generation for realistic images

$0.0006/ imageDefault
Run

Lightweight hand mask generation for realistic images

$0.0013/ imageDefault
Run

Higher-accuracy face mask generation for realistic images

$0.0006/ imageDefault
Run

Preprocessing

View all

Content-shuffle preprocessor for color and texture transfer with looser spatial control

$0.0006/ imageDefault
Run

Tile-based preprocessor for detail reconstruction, enhancement, and local consistency

$0.0006/ imageDefault
Run

Soft-edge preprocessor for gentler contour guidance than hard Canny boundaries

$0.0006/ imageDefault
Run