PaSanctuary

PaSanctuary is an AI-driven high-end image stylization model that focuses on creating a visual effect of tranquility, mystery and beauty, giving images a dreamlike artistic style. Through unique color rendering and light and shadow processing, PaSanctuary helps creators create a tranquil, peaceful but meaningful visual atmosphere, suitable for illustration creation, concept art, visual novels and brand image design.

Features

• Multi-dimensional style rendering: supports multiple style options from soft and quiet to mysterious dark colors.

• Dynamic light and shadow control: enhance the sense of space in the picture and simulate natural and soft light effects.

• Advanced color balance: automatically optimize hue, contrast and saturation for perfect visual presentation.

• High-resolution output: suitable for digital and print scenes, maintaining detail clarity.

• Style customization function: users can manually adjust the image effect to create a unique style.

Features

• Quiet and beautiful style: let the work show tranquility and fantasy, and enhance artistic expression.

• High degree of freedom creation: support a variety of preset styles and parameter adjustments to meet different creative needs.

• Powerful light and shadow simulation: truly restore natural light effects and enhance the immersive feeling of the picture.

• Adapt to multiple scenes: whether it is concept design, illustration creation, or visual narrative, it can do it.

Highlights

• Blending fantasy and reality: creating a highly artistic visual experience.

• One-click stylization conversion: save creation time and improve work efficiency.

• High-precision detail presentation: Make the image more vivid and realistic in detail processing.

• Continuously update the style library: Provide users with more visual creation possibilities.

V5:

This Checkpoint is trained on the awesome Basemodel NoobAI-XL V1.1.

The only prompt you ever need is this positive prompt:

masterpiece, best quality, newest, absurdres, highres

Default negative Prompt:

worst quality, old, early, low quality, lowres, bad hands, mutated hands, greyscale

Additional options for Style change are:

• realistic

No need for any additional negatives. Anything else for tag related stuff, see Basemodel NoobAI-XL V1.1.

This model is designed to work with resources trained on NoobAI-XL V1.1. Other SDXL or pony resources may not work.

I also recommend to use the Extension Adetailer.

Settings for generating Images for V5:

• Sampler: Euler a

• Steps: 30

• CFG 6.0

• Base Resolution 1024x1024

Recipe:

Merge to Checkpoint: TCV Style LoRA Restart Illustrious-XL + NoobAI-XL V1.1.

No additional Merge with block weights, adjustment and clip/tenc.