Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,84 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
-
## CyberRealistic
|
5 |
|
6 |
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: creativeml-openrail-m
|
3 |
+
tags:
|
4 |
+
- stable-diffusion
|
5 |
+
- sd-1.5
|
6 |
+
- text-to-image
|
7 |
+
- photorealistic
|
8 |
+
- semi-realistic
|
9 |
+
- cyberrealistic
|
10 |
+
- image-generation
|
11 |
+
- diffusers
|
12 |
+
model-index:
|
13 |
+
- name: CyberRealistic Semi-Real
|
14 |
+
results: []
|
15 |
---
|
|
|
16 |
|
17 |
+
# CyberRealistic Semi-Real
|
18 |
+
|
19 |
+
**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.
|
20 |
+
|
21 |
+
---
|
22 |
+
|
23 |
+
## 🧠 Model Details
|
24 |
+
|
25 |
+
- **Model Type**: Text-to-Image Generation
|
26 |
+
- **Base Model**: Stable Diffusion 1.5 (SD 1.5)
|
27 |
+
- **Format**: `safetensors`
|
28 |
+
- **Version**: Semi-Real
|
29 |
+
- **Creator**: [Cyberdelia](https://civitai.com/user/Cyberdelia)
|
30 |
+
- **File Size**: ~6.3 GB
|
31 |
+
- **License**: [CreativeML Open RAIL++-M License](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
|
32 |
+
|
33 |
+
---
|
34 |
+
|
35 |
+
## ✨ Features
|
36 |
+
|
37 |
+
- **Semi-Realistic Aesthetic**: Generates images that combine realistic details with stylized elements.
|
38 |
+
- **Ease of Use**: Designed for simplicity; achieves impressive results with straightforward prompts.
|
39 |
+
- **Integrated VAE**: Comes with a baked-in Variational Autoencoder for enhanced image quality.
|
40 |
+
- **Versatility**: Suitable for various applications, including character design, illustrations, and concept art.
|
41 |
+
|
42 |
+
---
|
43 |
+
|
44 |
+
## 🛠️ Recommended Settings
|
45 |
+
|
46 |
+
| Parameter | Recommended Value |
|
47 |
+
|-----------------|------------------------------------------------|
|
48 |
+
| Sampling Steps | 25–30 |
|
49 |
+
| Sampler | DPM++ 2M Karras / Euler A |
|
50 |
+
| Resolution | 512x512 (native), higher with Hires.fix |
|
51 |
+
| Hires Upscaler | 4x_NMKD-Siax_200k or 4x_NickelbackFS_72000_G |
|
52 |
+
| CFG Scale | 7.0–8.0 |
|
53 |
+
| VAE | Already baked-in |
|
54 |
+
|
55 |
+
---
|
56 |
+
|
57 |
+
## 🧾 Example Prompts
|
58 |
+
|
59 |
+
> (masterpiece, best quality), ultra-detailed, semi-realistic illustration of a character, natural lighting, depth of field, vibrant colors, soft cinematic bokeh
|
60 |
+
|
61 |
+
> (masterpiece, semi-realistic), stylized portrait, close-up, dramatic lighting, textured skin, shallow depth of field, soft shadows
|
62 |
+
|
63 |
+
|
64 |
+
---
|
65 |
+
|
66 |
+
## 🔗 Links
|
67 |
+
|
68 |
+
- [Civitai Model Page](https://civitai.com/models/464146/cyberrealistic-semi-real)
|
69 |
+
|
70 |
+
---
|
71 |
+
|
72 |
+
## 🚫 Limitations
|
73 |
+
|
74 |
+
- May produce content that could be considered sensitive; use responsibly.
|
75 |
+
- Some prompts involving abstract or highly stylized content may not perform as well due to the model's semi-realistic focus.
|
76 |
+
- Lighting and textures may occasionally be too clean or smooth depending on sampling choices.
|
77 |
+
|
78 |
+
---
|
79 |
+
|
80 |
+
## ✅ License
|
81 |
+
|
82 |
+
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.
|
83 |
+
|
84 |
+
> [License details](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
|