Illumira EVO is a fine-tune anime-focused model designed to produce high-quality, clean, and visually striking anime-style illustrations.
This is a v-pred version model, which requires skilled prompting to achieve better image results compared to the eps version. For guidance on using v-pred models effectively, please refer to the documentation.
Key Features
• Supports character tags and artist-style tags
• Delivers clean lines, expressive faces, and dynamic poses
• Balanced for both soft pastel styles and vivid lighting
Recommended Parameters
• Steps: 20–30
• CFG Scale: 3–7
• Sampler: Euler A
• Upscale: R-ESRGAN 4x+ Anime6B
You’re encouraged to experiment with different parameters and combine LoRA models to fine-tune character traits, outfits, expressions, or stylistic effects.
Usage Guidelines & Disclaimer
• Do not use this model to sell raw or unedited generations. Commercial use requires the output to be edited or converted to black and white.
• Prohibited: Any use involving illegal, harmful, or unethical content.
• The creator is not responsible for any legal issues resulting from misuse. Use at your own discretion.
For inquiries or feedback:
Discord: @LucyMocchi
Description
This is my first v-pred model, still in the experimental stage, so feel free to try it out. It requires skilled prompting to achieve better image quality than the eps version and uses the Illustrious-XL v2.0 VAE to reach resolutions up to 1536. For tips on getting the best results, please refer to the v-pred usage documentation.