Apparently it's incredible difficult for the existing models to generate images with this fantastic, nerdy and practical piece of garment, so I decided to have a go at training a Lora. I seem to get the best results around 0.8-0.9. Updated 26/7-23.
white man short hair 35yo wearing a blue anorak with big hood standing next to a creek, beige baggy cargo pants, mountains in the background, lake, uhd, hdr, realistic photo, golden hour, full body shot, fine detail, sharp photo, canon 5d, natural ligthning, good contrast <lora:Anorak:1>
<lora:Anorak_Lora:1> white man 35yo wearing a blue anorak with big hood standing next to a creek, beige baggy cargo pants, mountains in the background, lake, uhd, hdr, realistic photo, golden hour, full body shot, fine detail, sharp photo, canon 5d, natural ligthning, good contrast
raw photo, (full body photo:1.4), 1guy, handsome young white man, wearing beige loose baggy cargo pants, standing in the forest, golden hour, wearing a red anorak, hdr, tack sharp <lora:Anorak_Lora:0.8>
alexis-10000, outside in the rain, soaking wet, (detailed facial features:1.15), very long flowing hair, Unreal Engine 5, 8K, HQ, HDR, amazing detail, intricate details, shallow depth of field, reflections, art by artgerm and greg rutkowski
You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.