Use better input pics, and even then many of pics are unusable and have artefacts. Reality of new tech
@levelsio
-
Stable Diffusion Fine-tuned on Thousands of Images
By
–
Stable Diffusion then finetuned on thousands pics
-
Linode Storage Infrastructure Cost Efficiency Analysis
By
–
Linode! No big deal, terrabytes are cheap
-
Dreambooth vs Large-Scale Training: AI Model Fine-Tuning Techniques
By
–
So dreambooth is usually 10-20 pics of one person. This is thousands of random pics to improve it. Both similar technique but slightly different approach
-
Fine-tuning Stable Diffusion: The Future of Image Generation
By
–
@EmadGG was right, it'll all be about finetuning Stable Diffusion from here onwards
-
AI-Generated Person Looks Surprisingly Realistic
By
–
This person esp looks quite real to me, I'm kinda shocked
-
Imperfections Make Content More Authentically Human
By
–
Few more I liked: A lot more human than before, more imperfections = good
-
Training Custom Stable Diffusion Model with Personal Dataset
By
–
Pics of my first FULLY self trained Stable Diffusion (not Dreambooth) with my own data set These are just samples as it's not even fully done training Will train on men next! Then a combo model