My eighth Overwatch LORA. 2 versions - without <a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/a1111-sd-webui-locon">LoCon</a>, and experimental one with, example prompts\seeds same between versions. Focused on original appearance.<ul><li>Face - reinhardt, old man, white hair, scar across eye, beard</li><li>Armor - power armor, helmet, lion shield</li><li>Weapon - warhammer, holding hammer</li><li>Accessories - lion shield, animal print</li></ul>Checked strength range is 0.7-0.9, but feel free to experiment. Eyes are a bit finicky cause of the scar, and because they rather small by themselves.Can't tell for sure if there's noticeable enough difference in quality with LoCon version to switch, so let me know if there's any big differences for you. I probably haven't done the best possible job with implementing it, so I will keep experimenting with it for a few more LORA's.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 and CLIP Skip 2.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).

Reinhardt (Overwatch) LORA

Dataset of 28 images with deepbooru tags.

Files with SHA256: 9d08641dc9993f959ac1dc4072ab406d633a410f6d6bedfd572e7d8ead40c615