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.
๐ง Model Details
- Model Type: Text-to-Image Generation
- Base Model: Illustrious-XL
- Format:
safetensors
- Creator: Cyberdelia
- License: CreativeML Open RAIL++-M License
โจ 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.
๐ ๏ธ 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 |
๐งพ 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
๐ธ Example Outputs
- Downloads last month
- 330
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support