D.VA 2

https://s2.xiaonaofu.top/material/dcd50f33-20a4-461c-be75-02fde462a3a7.jpeghttps://s2.xiaonaofu.top/material/b2c0c2f5-3c39-44b5-b7cd-2c835ab6ec0a.jpeghttps://s2.xiaonaofu.top/material/6ad8952b-3fa9-4c10-aded-3385e277ed3c.jpeghttps://s2.xiaonaofu.top/material/2d381630-4f87-4a73-bc06-f70daf6653e2.jpeghttps://s2.xiaonaofu.top/material/cf5ccbfc-5bfd-43aa-97d1-d0fe49fffe8a.jpeghttps://s2.xiaonaofu.top/material/1020f27c-3caa-489c-84e4-37c07bab6015.jpegMy fifth Overwatch LORA. Mainly focused on original appearance + a bit of Academia skin.

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.

Academia – d.va, alternate hairstyle, twin braids, blazer, bespectacled, glasses, school uniform, pleated skirt

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:

Outfit – bodysuit, headphones, pilot suit, ribbed bodysuit, shoulder pads, turtleneck, thigh boots, thighhighs

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

Making and testing LORA’s takes quite a bit of my time, so I would appreciate if you bought me a coffee (you can also commision me there). I also have a Patreon if you prefer to support through there.

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 512×768, without HighRes.fix (mostly), using OrangeCocoa 50/50 Mix , with OrangeMix VAE, and using EasyNegative embedding, CLIP Skip 2. Inpaint examples are txt2img with 1 single inpaint done on face (I will comment on exceptions).

发表回复

后才能评论