realistic-vision-inpaint-coreml

Realistic Vision V6.0 Inpainting (Core ML)

This is a Core ML conversion of Realistic Vision V6.0 Inpainting - a photorealistic inpainting model optimized for Apple Silicon.

Model Details

Intended Use

This model is optimized for:

• iOS/macOS Deployment: Native Apple Silicon inference
• Photorealistic Inpainting: Natural-looking edits
• Portrait Editing: Face and skin retouching
• Photo Manipulation: Realistic object replacement

Capabilities

• Photorealistic Output: Superior realism compared to base SD
• Portrait Specialization: Excellent at faces and skin
• Detailed Textures: Realistic materials and lighting
• NSFW Safety Filter: Includes SafetyChecker for content filtering

Bundle Contents

• TextEncoder.mlmodelc - CLIP text encoder
• Unet.mlmodelc - 9-channel UNet for inpainting
• VAEDecoder.mlmodelc - Variational autoencoder decoder
• VAEEncoder.mlmodelc - Variational autoencoder encoder
• SafetyChecker.mlmodelc - NSFW content filter
• vocab.json - Tokenizer vocabulary
• merges.txt - BPE merges

Usage

Compatible with Apple's ml-stable-diffusion framework and iOS apps using Core ML.

License

This model is released under the CreativeML Open RAIL-M license.

Attribution

• Original Model: Realistic Vision V6.0 Inpainting by SG_161222
• Core ML Conversion: jc-builds