Edit model card

This is a a Textual Inversion Embedding to create an abstract style with a lot of detail, but still recognizable content.

Works with the 768x768 versions of Stable Diffusion 2.0 and 2.1

To use it put the painted_abstract.pt file in in your embeddings folder and use painted_abstract as promt

I recommend a cfg below 10 and maybe even a bit lower for 2.1, it gets more blocky the higher the cfg

usually I use 7 for 2.0 and 5 for 2.1

I also recommend using an anime upscaler like RealESRGAN_x4plus_anime_6B

For the examples I used different samplers and both 2.0 and 2.1, generated at 768x768 and upscaeld x4 with RealESRGAN_x4plus_anime_6B, otherwise untouched

09994-3570179826-(Horrifying Digital Artwork_1-0000.jpg 00009.jpg 11085-1189634371-(Vector image_1-0000.jpg 00012.jpg 09993-3530690305-(Horrifying Digital Artwork_1-0000.jpg 11057-956511450-(Drawing_1-0000.jpg 10017-1188724224-(Horrifying Digital Artwork_1-0000.jpg 10214-2903346083-(Magical Painting_1.3) of (Illustration_1-0000.jpg 10316-2083980865-(Drawing_1.2) of (Detailed illustration_1.2),(Evil_1-0000.jpg 10512-1292097722-(Detailed illustration_1.2),(Evil_1-0000.jpg 00007.jpg 10577-3820618625-(Magical Painting_1.2) of (Visual novel_1.2),(Energetic_1-0000.jpg 10774-1832682202-(Drawing_1.2) of (Sketched_1-0000.jpg 10917-114459484-(Digital Artwork_1-0000.jpg 11032-4026688857-(Drawing_1-0000.jpg 00004.jpg 11062-3333540938-(Professional 3D rendering_1-0000.jpg 11121-837666352-(Painting_1-0000.jpg 11186-442099512-(Painting_1-0000.jpg 11187-1398713543-(Professional 3D rendering_1-0000.jpg 11188-1848306607-(Digital Artwork_1-0000.jpg 11196-3753636034-(Photo_1-0000.jpg 00010.jpg

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .