Adolf DiffusionIMPORTANT NOTES:&gt;This model is NOT meant to share or glorify any political view.&gt;Trigger word: "AdolfHitler". Recommended weight: 0.7 and higher&gt;Trained on b&amp;w pictures, in order to get good results appropriate prompting and model is required.&gt;The best results achieved with realistic models (<a target="_blank" rel="ugc" href="https://civarchive.com/models/4201/realistic-vision-v13-fantasyai">Realistic Vision</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/4823/deliberate">Deliberate</a>).&gt;Probably the easiest way is to just use inpaint.Prompting&gt;To get images in color use these:<ul><li>Positive: in color</li><li>Negative: monochrome, black and white, b&amp;w, greyscale</li></ul>&gt;To get rid of blurry background:<ul><li>Negative: simple background, blurry background</li></ul>&gt;Trained mostly on upper body pictures, might be hard to get full body.&gt;If you have problems with getting Adolf's mustache, try setting the LoRa weight higher (or first generate image with low weight and then inpaint face with high weight).&gt;Eyes might sometimes be a problem, try experimenting with these:<ul><li>Positive: looking at viewer, detailed eyes etc.</li></ul>How to make similar modelI know this model is far from being great, but if someone wants to know the workflow, here you go:1. Find good image and crop it (in my case 44 images). 2. Upscale it x2~x4 (in my case mostly R-ESRGAN). 3. Remove noise using any graphic software. 4. Scale down 5. Train LoRa (using Google Colab).Also:&gt;Some of example images were created using ControlNet and img2img&gt;If you want to use my model anywhere feel free to do so, but it would be nice to put me in credits.&gt;For any questions you can contact me rafikxd123#7133

Files with SHA256: 24752ab128d9334f653bc4e08b421653b5426344b1437e9caceade67fcf7471a