<p>Currently works well with close-up photos of face, shots made from further away look bad - training data has only head shots.</p><p>Trigger word is <strong>HanniPham</strong>. I used 0.9-1.0 strength in my testing. If the face becomes oversaturated/contrasty then add "soft light, pale skin, smooth skin, soft lighting".</p><p>I used 512x512 imaged for training but 512x768 generations work well too. Use Img2Img for upscaling. Higher resolutions can cause twins.</p><p>This is work in progress model, I am planning to update the model with medium and further away shot in the future. Trained on ChilloutMix.</p><h3>DO NOT USE THIS MODEL TO CAUSE HARM TO ANYONE!</h3><h3>DO NOT USE FOR COMMERCIAL PURPOSES!</h3><h3>I AM NOT RESPOSIBLE FOR THE THINGS YOU CREATE WITH THIS MODEL!</h3><h3>DO NOT CREATE NSFW OR SLANDEROUS IMAGES WITH THIS MODEL, THIS IS MEANT FOR THE FANS OF THE ARTIST!</h3>

Hanni from NewJeans

<p>V1.0 trained on 35 512x512 images. Only head shots, lacks the ability to reproduce Hanni's face for medium and far away shots.</p>

Files with SHA256: 2e76b6fe6e1cf67a6af8a7ef976ecb45910b9d8c2ffd3b4d6d5392989bcdd990