My fifth Overwatch LORA. Mainly focused on original appearance + a bit of Academia skin.<ul><li>Original - prompt is d.va , I chose not to burn in her hair fully so you more easily could change hairstyles (for example ponytail), trigger for authentic one is simply long hair.</li><li>Academia - d.va, alternate hairstyle, twin braids, blazer, bespectacled, glasses, school uniform, pleated skirt</li></ul>Checked strength range is 0.6-0.8.Slight issue is headphones - there's barely any images, let alone good ones with D.Va without her headphones. As result - it's rather hard to get rid of them with original skin, and just a bit easier with Academia.Triggers for paticular things are:<ul><li>Outfit - bodysuit, headphones, pilot suit, ribbed bodysuit, shoulder pads, turtleneck, thigh boots, thighhighs</li><li>Accesories - bunny print (rabbit logo, easy to inpaint to fix one on bodysuit, or to add it on other things), clothes writing, headphones, bubblegum, finger gun</li></ul>If you liked my work, you can donate <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/gertan">here</a>.Review and comment with your experiences, I would appreciate whatever feedback you can provide in order to continue improving my technique.Trained on Anything V4.5 with anime.vae.pt.Samples are 512x768, without HighRes.fix (mostly), using <a target="_blank" rel="ugc" href="https://civarchive.com/models/4355/orangecocoa-5050-mix">OrangeCocoa 50/50 Mix</a> , with <a target="_blank" rel="ugc" href="https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/VAEs/orangemix.vae.pt">OrangeMix VAE</a>, and using <a target="_blank" rel="ugc" href="https://civarchive.com/models/7808/easynegative">EasyNegative</a> embedding, CLIP Skip 2. Inpaint examples are txt2img with 1 single inpaint done on face (I will comment on exceptions).

D.Va (Overwatch) LORA

Dataset of around 100 images with deepbooru tags.

Files with SHA256: 29acb459c2c6f4929e1e5937d18afa85b56bfcccc823943f62ce011805f32f70