Quillworks2.0 illustrious checkpoint

CHECKPOINT
Original


Updated:

✅ Key Features

  • Painterly & Cartoon Focus: Default style leans into digital painting and stylized cartoon, but still supports oil painting, anime, sketch, brushwork, and semi-realism when prompted.

  • Improved Anatomy: Stronger rendering of hands, faces, and limbs — particularly in character-focused prompts.

  • Prompt Adherence: Significantly improved tagging and dataset curation enables better control and style guidance.

  • Fast + Efficient: Excellent results on even lower end GPUs, making it highly cost-effective for local and online use.

  • Cohesive Backgrounds: Solid environmental structure and lighting, especially in portrait scenes.

⚠ Limitations

As with all Illustrious-style models, minor visual quirks may still occur:

  • Occasional extra fingers or facial distortion

  • Some stylistic blending when pushing for styles

  • Background details can vary depending on prompt complexity

🎯 Best Use Cases

  • Character illustration

  • Fantasy and sci-fi portraits

  • Digital painting landscapes

  • RPG Characters and NPCs

  • Webcomics and visual novels

  • Stylized concept art and worldbuilding

USAGE GUIDE

This runs well in Comfyui and Forge

DPM++ 2M SDE, Karras

20-40 Steps

Portrait, Square, and Landscape resolutions for illustrious all acceptable

CFG recommended to be 5. Don't be afraid to turn it up or down, I've found good results between 3 and 8.

Prompting "masterpiece Quality, [style], [subject], [background], [color theme], [extra details]"

Negative prompt "Text, Watermark, signature, [anything extra you see but don't want]"

Version Detail

Illustrious
7000
2
✅ Key Features Painterly & Cartoon Focus: Default style leans into digital painting and stylized cartoon, but still supports oil painting, anime, sketch, brushwork, and semi-realism when prompted. Improved Anatomy: Stronger rendering of hands, faces, and limbs — particularly in character-focused prompts. Prompt Adherence: Significantly improved tagging and dataset curation enables better control and style guidance. Fast + Efficient: Excellent results on even lower end GPUs, making it highly cost-effective for local and online use. Cohesive Backgrounds: Solid environmental structure and lighting, especially in portrait scenes. ⚠ Limitations As with all Illustrious-style models, minor visual quirks may still occur: Occasional extra fingers or facial distortion Some stylistic blending when pushing for styles Background details can vary depending on prompt complexity 🎯 Best Use Cases Character illustration Fantasy and sci-fi portraits Digital painting landscapes RPG Characters and NPCs Webcomics and visual novels Stylized concept art and worldbuilding USAGE GUIDE This runs well in Comfyui and Forge DPM++ 2M SDE, Karras 20-40 Steps Portrait, Square, and Landscape resolutions for illustrious all acceptable CFG recommended to be 5. Don't be afraid to turn it up or down, I've found good results between 3 and 8. Prompting "masterpiece Quality, [style], [subject], [background], [color theme], [extra details]" Negative prompt "Text, Watermark, signature, [anything extra you see but don't want]"

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts