This is a textual inversion embedding for Brigitte (Lindholm) from Overwatch.
Use corneo_brigitte to activate. The eyes are pretty bad in the embedding by itself, so you'll definitely want to prompt for the eyes to be a bit better, or just inpaint them after generating the rest of the image. I don't think this one works quite as well as my other character embeddings but it was a request so here it is! Also the training data may have gone a bit too hard on the muscular female approach, so unless you like your ladies with a LOT of muscles, you probably want to put (muscular:0.6) or thereabouts in your negative prompt.
Example images produced with OrangeCocoa available here https://civarchive.com/models/4355/orangecocoa-5050-mix
Check out my other civitai models for more characters and sex positions! https://civarchive.com/user/Master_Corneo
If you enjoy this embed, I genuinely love seeing your creations with it - you can attach them to a review if you're not aware (but not comments sadly)!
Description
FAQ
Comments (15)
bro yes thank you. is tracer in the works?
I wasn't planning it, but, eh, maybe. The more I do, the more it would feel like the rest are missing out :)
what is corneo_arm_grab_missionary word ? an other textual inversion ?
Yes it's another textual inversion but one I've not released yet because the results are usually not very good, and I'm planning to re-train it at some point first
I am very much looking forward to its arrival
Found out about a problem today which has probably made all my embeds do far worse than they would have been otherwise! So there's a chance that retaining it now will work out, but no guarantees yet
Please tell me. I think I'm doing everything right, setting the same settings, remembering the model. But the results, although similar to Brigitte, but my tips almost do not work =(
Have you tried copying the prompts from one of my examples exactly? The embedding listed last in the prompt can help as they overpower most normal tags. Can also de-emphasise it with something like (corneo_brigitte:0.9)
What checkpoint do you use for textual inversion training? i fail everytime i try :(
Just NAI, no hyper network or VAE
i see i will try, its getting a nightmare, because the horns on the character i try to train are not working right
Ah yeah that can be tricky
One last question if you dont mind, do you train at 512x512 or higther?
Yep 512x512, I do just follow this simplified guide https://rentry.org/simplified-embed-training
Ty!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.