Katsura Masakazu Style

Reviews are very appreciated and show me you enjoy my work, keeping me motivated in releasing more Models in the future! Would love to see the community create images with my work.

Because of the low Dataset on danbooru the base Illustrious/NoobAI Models can't really do this artists style very well.

Best Results are at 1 weight & using the trigger word:

Katsura Masakazu

v1.0 (NoobAI EPS)

Trained on the base NoobAI 0.75 EPS Version model for compatibility with all other NoobAI models. I chose 0.75 because of lower saturation of colors from the base model.

All preview images are created using the NoobAICyberFix 3.0 Checkpoint.

Best Results are at 0.8 weight & using the trigger word:

Katsura Masakazu

The settings used to create the images were:

Steps: 30
CFG: 6
Sampler: Euler
Scheduler: SGM_Uniform
Denoise: 1

v1.0 (IL)

Trained on the base Illustrious XL 1.0 model for compatibility with all other Illustrious models.

You can see a comparison between just the tag itself and the influence with the LoRA here. The difference is huge.

All preview images are created using the NoobAI-XL Epsilon-pred 1.1-Version.
The comparison images in the table were made by using the same seed and settings with different prompts using the normal Illustrious-XL Model.

Best Results are at 1 weight & using the trigger word:

Katsura Masakazu

The settings used to create the images were:

Steps: 30
CFG: 5
Sampler: Euler
Scheduler: Normal
Denoise: 1

All images were upscaled using the Remacri-4x Model.
All images were generated using my ComfyUI workflow that you can find here, attached to preview images or in the suggested resources. This includes a Detailer that automatically inpaints body parts like eyes, lips, hands etc.
So if your results do not match mine it's probably because of this. I recommend using the workflow which is also attached to every image.