---
title: cyberrealisticPony_v12
canonical_url: "https://www.modelscope.cn/models/lc4180531/cyberrealisticPony_v12"
md_url: "https://www.modelscope.cn/models/lc4180531/cyberrealisticPony_v12.md"
repository: lc4180531/cyberrealisticPony_v12
chinese_name: "cyberrealisticPony_v12小马"
last_updated: 2025-06-22
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - stabilityai/stable-diffusion-xl-base-1.0
base_model_relation: finetune
parameters: 3.5B
tensor_type:
  - F16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - Pytorch
supports_inference: txt2img
downloads: 727
stars: 12
tags:
  - Checkpoint
  - text-to-image
---

# cyberrealisticPony_v12

> cyberrealisticPony_v12 - lc4180531 在 ModelScope 开源的模型。CyberRealistic Pony is what happens when the charm of Pony Diffusion gallops headfirst into the photorealistic chaos of CyberRealistic. The result? A model that can do cutesy or sexy — or both — with…

lc4180531/cyberrealisticPony_v12 是 ModelScope 魔搭社区上的 3.5B 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 stabilityai/stable-diffusion-xl-base-1.0 构建，并支持在线推理（txt2img）。

- **Repository**: lc4180531/cyberrealisticPony_v12
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 3.5B
- **Base model**: stabilityai/stable-diffusion-xl-base-1.0
- **Online inference**: txt2img
- **Tags**: Checkpoint, text-to-image
- **Downloads**: 727
- **Stars**: 12
- **Last updated**: 2025-06-22

Source: https://www.modelscope.cn/models/lc4180531/cyberrealisticPony_v12

---

搬运于C站，原作者：Cyberdelia

🐴 CyberRealistic Pony
Pony Diffusion just got a glow-up.

CyberRealistic Pony is what happens when the charm of Pony Diffusion gallops headfirst into the photorealistic chaos of CyberRealistic. The result? A model that can do cutesy or sexy — or both — with ultra-detailed textures, cinematic lighting, and a little spark of AI magic.

Whether you're wrangling anthro aesthetics or chasing equine dreams with near-human realism, this model knows how to strut. It’s wild, whimsical, and unapologetically sharp.



🧠 How to Use It

Sampling method: DPM++ SDE Karras / DPM++ 2M Karras / Euler a
Sampling steps: 30+ Steps
Resolution: 896x1152 / 832x1216
CFG: 5
Clip Skip: 2


✅ Recommended Prompts

score_9, score_8_up, score_7_up, (SUBJECT), 
Negative Prompt examples:

score_6, score_5, score_4, (worst quality:1.2), (low quality:1.2), (normal quality:1.2), lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, extra limb, missing limbs
score_6, score_5, score_4, simplified, abstract, unrealistic, impressionistic, low resolution, lowres, bad anatomy, bad hands, missing fingers, worst quality, low quality, normal quality, cartoon, anime, drawing, sketch, illustration, artificial, poor quality


🛠 ADetailer Settings

Adetailer model: face_yolov9c.pt
If you only want the main face being refined set 'Mask only the top k largest' to 1.


⚠️ Disclaimer
This model can output sensitive content. You are fully responsible for what you create with it. Don't do weird stuff and then blame the horse.
SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('lc4180531/cyberrealisticPony_v12')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/lc4180531/cyberrealisticPony_v12.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>