Gatchamn/coreml-realvisxl-v5-lightning-8bit

RealVisXL V5.0 Lightning — Core ML (8-bit)

_{Reference image for this model. Curated from the model's own examples — not generated from this Core ML build; quantized output may differ slightly.}

Photorealism specialist — realistic people and scenes, few-step.

Core ML conversion for Apple silicon (iOS / iPadOS / macOS, Neural Engine), built with Apple's ml-stable-diffusion for mindfire-image.

Original model

Converted from SG161222/RealVisXL_V5.0_Lightning — go there for the original weights, full model card and licence.

Demo prompt

The prompt and settings used for this model's demo image (also the reference example shipped in mindfire-image):

Prompt

photo of a woman in a rain-soaked city street at night, neon reflections, shallow depth of field, natural skin texture

Negative prompt

(octane render, render, drawing, anime, bad photo, bad photography:1.3), (worst quality, low quality, blurry:1.2), (bad teeth, deformed teeth, deformed lips), (bad anatomy, bad proportions:1.1), (deformed iris, deformed pupils), (deformed eyes, bad eyes), (deformed face, ugly face, bad face), (deformed hands, bad hands, fused fingers), morbid, mutilated, mutation, disfigured

Setting	Value
Steps	5
Guidance (CFG)	1.5
Size	1024x1024

5-8 steps at CFG 1.5-2.0.

Modifications from the base model

Converted from PyTorch/diffusers to Core ML (.mlmodelc) and quantized to 8-bit palettized weights. No fine-tuning — behaviour tracks the base model, though quantization can shift outputs slightly.

Licence

Inherited from the base model: openrail++. This carries the OpenRAIL use-based restrictions (Attachment A), which bind you as a downstream user of this conversion exactly as they do for the base model. Read the base model's licence before use or redistribution.