Text-to-Image
Diffusers
stable-diffusion
sdxl
photorealistic
cyberrealistic
illustrious
image-generation
Instructions to use cyberdelia/CyberIllustrious with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use cyberdelia/CyberIllustrious with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("cyberdelia/CyberIllustrious", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
CyberIllustrious | CyberRealistic
CyberIllustrious (also known as CyberRealistic) is a photorealistic adaptation of the Illustrious-XL checkpoint, designed to produce stunningly realistic images with ease. Developed by Cyberdelia, this model excels in generating high-quality visuals, particularly in portrait and editorial-style scenes.
🧠 Model Details
- Model Type: Text-to-Image Generation
- Base Model: Illustrious-XL
- Format:
safetensors - Creator: Cyberdelia
- License: CreativeML Open RAIL++-M License
✨ Features
- Photorealism: Generates highly detailed and realistic images, especially effective for human subjects.
- Ease of Use: 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 portraits, fashion, and cinematic scenes.
🛠️ Recommended Settings
| Parameter | Recommended Value |
|---|---|
| Sampling Steps | 30+ |
| Sampler | DPM++ SDE Karras / DPM++ 2M Karras / Euler a |
| Resolution | 896x1152 / 832x1216 |
| CFG Scale | 5 |
| VAE | Already baked-in |
🧾 Example Prompts
(masterpiece, best quality), ultra-detailed, realistic photo of a 22-year-old woman, natural lighting, depth of field, candid moment, color graded, RAW photo, soft cinematic bokeh
(masterpiece, photorealistic), editorial fashion photo, close-up, dramatic side lighting, textured skin, shallow depth of field, soft shadows
📸 Example Outputs
- Downloads last month
- 710
