Benito Mussolini LoCon

IMPORTANT NOTES:

>This model is NOT meant to share or glorify any political view.

>Trigger word: "BenitoMussolini". Recommended weight: 0.7

>Trained on mostly b&w pictures, in order to get good results appropriate prompting and model is required.

>The best results achieved with realistic models (tested with Realistic Vision).

>Probably the easiest way is to just use inpaint.

>This time I’m testing LoCon, feel free to post your feedback.

Prompting

>Highly recommended to add this to your prompt:

Positive: in color

Negative: oversaturated, comics, fake, black and white, b&w, blurry, image noise, simple background, monochrome, (scar)

>Trained mostly on upper body pictures, might be hard to get full body.

>Negative prompts are powerful, use them to your advantage.

>I suggest using 768x768 resolution.

How to make a similar model

I know this model is far from being great, but if someone wants to know the workflow, here you go:

1. Find good images and crop them. 2. Upscale x2~x4 (in my case mostly R-ESRGAN). 3. Remove noise using any graphic software. 4. Scale down. 5. Train LoCon (using Google Colab, e.g. Kohya Trainer). 6. This time I’ve experimented with block weight adjusting (check out sd-webui-lora-block-weight and sd-webui-supermerger awesome tools for LoRa fine tuning)

I mostly use b&w photos, so following steps 2,3,4 leads to significant increase of quality and reduction of image noise.

Also:

>Why do you share such controversial models?

Mainly for fun, also because I can as it’s allowed and I’m not doing anything illegal.

>If you want to use my model anywhere feel free to do so, but it would be nice to put me in credits.

>Check out my models: Adolf Diffusion, Stalin Diffusion

>For any question you can contact me rafikxd123#7133