---
license: creativeml-openrail-m
base_model: AstraliteHeart/pony-diffusion-v6
pipeline_tag: text-to-image
tags:
  - core-ml
  - coreml
  - stable-diffusion
  - apple-silicon
  - ios
  - quantized
---

# Pony Diffusion V6 XL — 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>

**Character specialist** — anthro / furry / cartoon / anime characters. Not a photoreal 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 **[AstraliteHeart/pony-diffusion-v6](https://huggingface.co/AstraliteHeart/pony-diffusion-v6)** — 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**
```
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_furry, beautiful female anthro shark portrait, dramatic lighting, dark background
```

| Setting | Value |
|---|---|
| Steps | 25 |
| Guidance (CFG) | 7.0 |
| Size | 1024x1024 |

> **This model needs score-tag prompting.** Always lead with
> `score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up`, then a
> `source_*` tag (`source_furry`, `source_anime`, `source_pony`, `source_cartoon`),
> then your description. Without the score prefix quality degrades badly.
> Use **CLIP skip 2**.

## 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.