README.md

---
license: creativeml-openrail-m
base_model: Lykon/dreamshaper-8
pipeline_tag: text-to-image
tags:
  - core-ml
  - coreml
  - stable-diffusion
  - apple-silicon
  - ios
  - quantized
---

# DreamShaper 8 — Core ML (8-bit)

![demo](demo.png)

<sub>Reference image for this model. Curated from the model's own examples — not generated from this Core ML build; quantized output may differ slightly.</sub>

Versatile all-rounder (SD 1.5) — art, fantasy, semi-realistic and anime in one model.

Core ML conversion for Apple silicon (iOS / iPadOS / macOS, Neural Engine), built with Apple's
[ml-stable-diffusion](https://github.com/apple/ml-stable-diffusion) for
[mindfire-image](https://github.com/Gatcha-man/mindfire-image).

## Original model

Converted from **[Lykon/dreamshaper-8](https://huggingface.co/Lykon/dreamshaper-8)** — 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**
```
portrait photo of muscular bearded guy in a worn mech suit, light bokeh, intricate, steel metal, elegant, sharp focus, soft lighting, vibrant colors
```

| Setting | Value |
|---|---|
| Steps | 25 |
| Guidance (CFG) | not specified |
| Size | 512x512 |

Native resolution is **512x512** (SD 1.5). The card documents 25 steps with a DEIS multistep scheduler; guidance is not stated.

## 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: `creativeml-openrail-m`. 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.