|
|
--- |
|
|
license: creativeml-openrail-m |
|
|
tags: |
|
|
- stable-diffusion |
|
|
- sd-1.5 |
|
|
- text-to-image |
|
|
- photorealistic |
|
|
- semi-realistic |
|
|
- cyberrealistic |
|
|
- image-generation |
|
|
- diffusers |
|
|
model-index: |
|
|
- name: CyberRealistic Semi-Real |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
# CyberRealistic Semi-Real |
|
|
|
|
|
**CyberRealistic Semi-Real** is a semi-realistic image generation model built upon the **Stable Diffusion 1.5 (SD 1.5)** architecture. Developed by [Cyberdelia](https://civitai.com/user/Cyberdelia), this model aims to produce images that blend photorealism with stylized elements, offering a unique aesthetic for various creative applications. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧠 Model Details |
|
|
|
|
|
- **Model Type**: Text-to-Image Generation |
|
|
- **Base Model**: Stable Diffusion 1.5 (SD 1.5) |
|
|
- **Format**: `safetensors` |
|
|
- **Version**: Semi-Real |
|
|
- **Creator**: [Cyberdelia](https://civitai.com/user/Cyberdelia) |
|
|
- **File Size**: ~6.3 GB |
|
|
- **License**: [CreativeML Open RAIL++-M License](https://huggingface.co/spaces/CompVis/stable-diffusion-license) |
|
|
|
|
|
--- |
|
|
|
|
|
## ✨ Features |
|
|
|
|
|
- **Semi-Realistic Aesthetic**: Generates images that combine realistic details with stylized elements. |
|
|
- **Ease of Use**: Designed for simplicity; achieves impressive results with straightforward prompts. |
|
|
- **Integrated VAE**: Comes with a baked-in Variational Autoencoder for enhanced image quality. |
|
|
- **Versatility**: Suitable for various applications, including character design, illustrations, and concept art. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🛠️ Recommended Settings |
|
|
|
|
|
| Parameter | Recommended Value | |
|
|
|-----------------|------------------------------------------------| |
|
|
| Sampling Steps | 25–30 | |
|
|
| Sampler | DPM++ 2M Karras / Euler A | |
|
|
| Resolution | 512x512 (native), higher with Hires.fix | |
|
|
| Hires Upscaler | 4x_NMKD-Siax_200k or 4x_NickelbackFS_72000_G | |
|
|
| CFG Scale | 7.0–8.0 | |
|
|
| VAE | Already baked-in | |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧾 Example Prompts |
|
|
|
|
|
> (masterpiece, best quality), ultra-detailed, semi-realistic illustration of a character, natural lighting, depth of field, vibrant colors, soft cinematic bokeh |
|
|
|
|
|
> (masterpiece, semi-realistic), stylized portrait, close-up, dramatic lighting, textured skin, shallow depth of field, soft shadows |
|
|
|
|
|
|
|
|
--- |
|
|
|
|
|
## 🔗 Links |
|
|
|
|
|
- [Civitai Model Page](https://civitai.com/models/464146/cyberrealistic-semi-real) |
|
|
|
|
|
--- |
|
|
|
|
|
## 🚫 Limitations |
|
|
|
|
|
- May produce content that could be considered sensitive; use responsibly. |
|
|
- Some prompts involving abstract or highly stylized content may not perform as well due to the model's semi-realistic focus. |
|
|
- Lighting and textures may occasionally be too clean or smooth depending on sampling choices. |
|
|
|
|
|
--- |
|
|
|
|
|
## ✅ License |
|
|
|
|
|
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. |
|
|
|
|
|
> [License details](https://huggingface.co/spaces/CompVis/stable-diffusion-license) |
|
|
|
