A highly flexible model for painterly and graphic styles. <h3 id="disclaimer:">Disclaimer:</h3>This is not my model, it was created by <a rel="ugc" href="https://tensor.art/u/802405053439862095">FlashfiringAi</a> and uploaded to Tensor and Shakker, but they don't post their models to Civitai. But it's an Illustrious model, which has a copyleft license and cannot place any restrictions on how and where people share it, so I'm posting it here. They have multiple other versions, but this is my favorite and a go-to for making concept art for me.

Quillworks2.0 Illustrious Simplified

quillworks20_v20.safetensors

v2.0

✅ Key Features<ul><li>Painterly &amp; Cartoon Focus: Default style leans into digital painting and stylized cartoon, but still supports oil painting, anime, sketch, brushwork, and semi-realism when prompted.</li><li>Improved Anatomy: Stronger rendering of hands, faces, and limbs — particularly in character-focused prompts.</li><li>Prompt Adherence: Significantly improved tagging and dataset curation enables better control and style guidance.</li><li>Fast + Efficient: Excellent results on even lower end GPUs, making it highly cost-effective for local and online use.</li><li>Cohesive Backgrounds: Solid environmental structure and lighting, especially in portrait scenes.</li></ul>⚠ LimitationsAs with all Illustrious-style models, minor visual quirks may still occur:<ul><li>Occasional extra fingers or facial distortion</li><li>Some stylistic blending when pushing for styles</li><li>Background details can vary depending on prompt complexity</li></ul>🎯 Best Use Cases<ul><li>Character illustration</li><li>Fantasy and sci-fi portraits</li><li>Digital painting landscapes</li><li>RPG Characters and NPCs</li><li>Webcomics and visual novels</li><li>Stylized concept art and worldbuilding</li></ul>USAGE GUIDEThis runs well in Comfyui and ForgeDPM++ 2M SDE, Karras20-40 StepsPortrait, Square, and Landscape resolutions for illustrious all acceptableCFG 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]"

Quillworks2.0 illustrious checkpoint

✅ 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]"

Files with SHA256: 31914dab2b09b7b29cd6b3e117eced12bb6ea201ab2ff94087ff28b1229a253d