coreml-cyberrealistic-v8-inpaint-fp16

CyberRealistic V8 Inpaint — Core ML FP16 for LocalMuse

This repository contains an unquantized FP16 Core ML conversion of CyberRealistic v8.0-Inpainting by Cyberdelia for the dedicated Inpaint workflow in the LocalMuse iOS app.

Provenance

• Official source: CyberRealistic v8.0-Inpainting, Civitai model version 1464918
• Authenticated checkpoint mirror: vclansience/SD_models
• Pinned mirror revision: a461e57d5b2d1975670b27580cc03b6d460caf2c
• Source file: cyberrealistic_v80Inpainting.safetensors
• Source size: 2132679962 bytes
• Source SHA-256: 0ee757321f40a95029c4ff7e4ae78352ed9ee67a3ddaa8d14b6b1a48161901f2
• Architecture: Stable Diffusion 1.5 Inpaint
• UNet input/output: [2, 9, 64, 64] → [2, 4, 64, 64]
• Fixed image resolution: 512×512
• Storage precision: FP16
• Quantization/palettization: none
• UNet attention graph: SPLIT_EINSUM_V2
• Core ML deployment target: iOS 17
• Core ML execution policy in LocalMuse: CPU + GPU
• Conversion tooling: Apple ml-stable-diffusion commit e12202c1f6405b83918b58a5d097cd61e3e1f702, Core ML Tools 8.3.0

The Hugging Face mirror is used because Civitai requires an interactive account for the original download. Its LFS SHA-256 exactly matches the official Civitai API fingerprint. Pipeline configuration is pinned separately to the official Stable Diffusion 1.5 Inpaint repository at revision 8a4288a76071f7280aedbdb3253bdb9e9d5d84bb.

The UNet is split into two compiled graphs so every weight file remains below 1 GB. The package includes the matching CLIP text encoder, VAE decoder, VAE encoder and tokenizer. PROVENANCE.json records the authenticated source, conversion dependencies and SHA-256 of every compiled runtime artifact.

This package is only compatible with a true nine-channel Inpaint runtime. It must not replace a normal four-channel SD 1.5 model.

Validation

• UNet parity: 74.5 dB PSNR
• CLIP text encoder parity: 82.5 dB PSNR
• VAE decoder parity: 61.7 dB PSNR
• VAE encoder parity: 79.6 dB PSNR
• Compiled UNet input: [2, 9, 64, 64]
• Compiled UNet output: [2, 4, 64, 64]

Recommended settings

• Scheduler: DPM-Solver++
• Steps: 30
• Guidance scale: 5.0
• Resolution: 512×512
• Batch size: 1 on iOS
• Device memory class: 8 GB minimum in LocalMuse

License and attribution

CyberRealistic is authored by Cyberdelia. The original Civitai model permits commercial use and derivative distribution. The underlying SD 1.5 terms and use-based restrictions are retained in the included CreativeML Open RAIL-M license.

The files here are modified by conversion to compiled Core ML FP16 format and by splitting the UNet graph. No weights were retrained, merged, quantized or palettized, and no additional restrictions are imposed. This repository does not imply endorsement by Cyberdelia, Stability AI, CompVis, Runway, Apple, Hugging Face or Civitai.