Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
-
## CyberRealistic
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Certainly! Here's a Hugging Face–ready `README.md` for **CyberRealistic Pony**, complete with YAML metadata and structured content:
|
| 2 |
+
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
```markdown
|
| 6 |
+
---
|
| 7 |
+
license: creativeml-openrail-m
|
| 8 |
+
tags:
|
| 9 |
+
- stable-diffusion
|
| 10 |
+
- sdxl
|
| 11 |
+
- text-to-image
|
| 12 |
+
- photorealistic
|
| 13 |
+
- cyberrealistic
|
| 14 |
+
- pony
|
| 15 |
+
- image-generation
|
| 16 |
+
- diffusers
|
| 17 |
+
model-index:
|
| 18 |
+
- name: CyberRealistic Pony
|
| 19 |
+
results: []
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
# CyberRealistic Pony
|
| 23 |
+
|
| 24 |
+
**CyberRealistic Pony** is a specialized photorealistic model based on **Stable Diffusion XL (SDXL)**, designed to generate lifelike images of pony characters with exceptional detail and realism. Developed by [Cyberdelia](https://civitai.com/user/Cyberdelia), this model excels in creating high-quality visuals that blend the charm of pony aesthetics with realistic textures and lighting.
|
| 25 |
+
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
## 🧠 Model Details
|
| 29 |
+
|
| 30 |
+
- **Model Type**: Text-to-Image Generation
|
| 31 |
+
- **Base Model**: Stable Diffusion XL (SDXL)
|
| 32 |
+
- **Format**: `safetensors`
|
| 33 |
+
- **Latest Version**: v1.0
|
| 34 |
+
- **Creator**: [Cyberdelia](https://civitai.com/user/Cyberdelia)
|
| 35 |
+
- **File Size**: ~6.5 GB
|
| 36 |
+
- **License**: [CreativeML Open RAIL++-M License](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
## ✨ Features
|
| 41 |
+
|
| 42 |
+
- **Photorealism**: Generates highly detailed and realistic pony images, capturing intricate textures and lighting.
|
| 43 |
+
- **Ease of Use**: Achieves impressive results with straightforward prompts.
|
| 44 |
+
- **Integrated VAE**: Comes with a baked-in Variational Autoencoder for enhanced image quality.
|
| 45 |
+
- **Versatility**: Suitable for various applications, including character design, illustrations, and concept art.
|
| 46 |
+
|
| 47 |
---
|
| 48 |
+
|
| 49 |
+
## 🛠️ Recommended Settings
|
| 50 |
+
|
| 51 |
+
| Parameter | Recommended Value |
|
| 52 |
+
|-----------------|------------------------------------------------|
|
| 53 |
+
| Sampling Steps | 30+ |
|
| 54 |
+
| Sampler | DPM++ SDE Karras / DPM++ 2M Karras / Euler a |
|
| 55 |
+
| Resolution | 896x1152 / 832x1216 |
|
| 56 |
+
| CFG Scale | 5 |
|
| 57 |
+
| VAE | Already baked-in |
|
| 58 |
+
|
| 59 |
---
|
|
|
|
| 60 |
|
| 61 |
+
## 🧾 Example Prompts
|
| 62 |
+
|
| 63 |
+
> (masterpiece, best quality), ultra-detailed, realistic photo of a pony character, natural lighting, depth of field, vibrant colors, soft cinematic bokeh
|
| 64 |
+
|
| 65 |
+
> (masterpiece, photorealistic), close-up of a pony with intricate mane details, dramatic side lighting, textured fur, shallow depth of field, soft shadows
|
| 66 |
+
|
| 67 |
+
---
|
| 68 |
+
|
| 69 |
+
## 📸 Example Outputs
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
---
|
| 75 |
+
|
| 76 |
+
## 🔗 Links
|
| 77 |
+
|
| 78 |
+
- [Civitai Model Page](https://civitai.com/models/443821/cyberrealistic-pony)
|
| 79 |
+
|
| 80 |
+
---
|
| 81 |
+
|
| 82 |
+
## 🚫 Limitations
|
| 83 |
+
|
| 84 |
+
- May produce content that could be considered sensitive; use responsibly.
|
| 85 |
+
- Some prompts involving abstract or non-pony content may not perform as well due to the model's specialized training.
|
| 86 |
+
- Lighting and textures may occasionally be too clean or smooth depending on sampling choices.
|
| 87 |
+
|
| 88 |
+
---
|
| 89 |
+
|
| 90 |
+
## ✅ License
|
| 91 |
+
|
| 92 |
+
This model is distributed under the **CreativeML Open RAIL++-M License**, which allows commercial and non-commercial use, with proper credit and no malicious usage.
|
| 93 |
+
|
| 94 |
+
> [License details](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
|
| 95 |
+
```
|
| 96 |
+
|