image-inpainting

What problem does it solve?

It solves the problem of precisely editing or removing unwanted regions in an image, such as deleting objects or watermarks without disturbing the rest of the photo.

Core Features & Use Cases

• Mask-driven inpainting: Replace regions defined by a grayscale mask while preserving unmasked areas.
• Fallback when no mask exists: Use description-based edit models to target a region described in words.
• Controlled model routing: Automatically selects the best inpainting or edit model depending on whether a mask is available.
• Use cases: Object removal, watermark removal, blemish cleanup, region replacement, and any controlled local edit defined by a binary mask.

Quick Start

Use the image-inpainting skill to replace a masked object by providing the source image URL, a grayscale mask URL, and a prompt describing what should appear in the masked area.