Realism By Stable Yogi SD 1.5 V9 LCM · Core ML 6-bit

This repository contains a reproducible Core ML format conversion for the LocalMuse iOS app. The original model was created by Stable Yogi. LocalMuseAI does not claim authorship of the source weights.

Source

Model: Realism By Stable Yogi (Pony)
Version: SD1.5_V9_LCM / Civitai version 1235013
Source file: realismByStableYogi_sd15V9LCM.safetensors
Source size: 2,132,626,090 bytes
Source SHA-256: 1a16a9524427019dc513b398087035e7e36ad2f2aa9691bd71d28ad959e94180
Source page: https://civitai.com/models/166609?modelVersionId=1235013

The source is an already-distilled SD 1.5 LCM checkpoint. No additional LoRA or merge was applied during conversion.

Core ML conversion

Fixed resolution: 512 × 512
Runtime: Stable Diffusion 1.5, four-channel UNet
Attention: SPLIT_EINSUM_V2
Unet.mlmodelc: Apple 6-bit k-means palettization
TextEncoder.mlmodelc: FP16
VAEDecoder.mlmodelc: FP16
VAEEncoder.mlmodelc: FP16
Converter: Apple ml-stable-diffusion revision e12202c1f6405b83918b58a5d097cd61e3e1f702

All source files are authenticated before tracing. Component-level PyTorch/Core ML parity checks are enabled during conversion. Exact source and artifact hashes are recorded in PROVENANCE.json.

LocalMuse settings

Scheduler: LCM
Default: 9 steps
CFG: 1.0
Resolution: 512 × 512

The upstream gallery examples use Euler a at 9 steps and CFG 1. LocalMuse uses its existing LCM scheduler because this is an LCM-distilled checkpoint and the same configuration was validated before conversion. Upstream textual-inversion trigger names are separate assets and are not included in this repository.

License and attribution

The model and this converted representation remain subject to the CreativeML Open RAIL++-M license in LICENSE, including its use-based restrictions. Modified files are identified here as a Core ML format conversion with 6-bit UNet palettization. No additional restrictions are imposed.

Original model creator: Stable Yogi
Format conversion: LocalMuseAI
Conversion tooling: Apple ml-stable-diffusion

Downloads last month: -; Downloads are not tracked for this model. How to track