IMPORTANT: This LoRA is trained as a V-Pred model and is fully compatible with other V-Pred models. For the best results, make sure to use it with a V-Pred checkpoint.
Trigger words:
octaviaHB, beak, colored sclera, pink sclera, white pupils, black hair, long hair
Outfit:
beanie, pink choker, black cardigan, long sleeves, hat, black leggings
Tested and used with WAI-SHUFFLE-NOOB:
https://civarchive.com/models/989367?modelVersionId=1202076
For on-site generations, use my Tensor Art page: https://tensor.art/u/830771749061779884
Join my Patreon for full access:
https://www.patreon.com/Waifu_Chef
Follow me on Twitter:
Check out my Pixiv gallery:
🎨 https://www.pixiv.net/en/users/111915639
Order a commission here!
https://ko-fi.com/c/38aa4a973d
Support my work by buying me a ko-fi:
Description
FAQ
Comments (8)
idk but v2 works absolutely terribly for my generation on site. It's pointless to even add it to other LoRAs about Octavia. Even if you just set it to the minimum value (0.8), it will ruin everything. Maybe I just haven't learned how to handle it yet, but I've already spent over a hundred buzzes to get used to this model and still
Sorry to hear that! Keep in mind that using too many LoRAs at once, along with pony tags like score_9, score_8_up, score_7_up, etc., can overcomplicate the prompt and affect results. Simplifying a bit might help a lot! For best results I recommend using Tensor Art for generation since it's better optimized for base model compatibility with this LoRA. Hopefully that helps get better outputs!
Waifu_Chef I like to use NTR-mix-noob-XL. But this version of LoRA does not give normal images neither with complex nor with simple prompt. It works normal only with WAI-NSFW-illustrious
Same v1 works better
genning with indigoFurryMixXL_noobaiEPS7 checkpoint results in glitches and visual mess on background
I recommend using a v-pred model, though this Octavia model is outdated. I’ll be updating it soon with newer screencaps and improved parameters!
Just tried version 3. Very nice rendering and adherence. A lot of the difficult things like the crown on the beanie, the eyes, beak, and the owl tail are really rendering well now. I think it’s a dramatic improvement over the prior version and very polished.
Glad to hear that! Appreciate the thoughtful feedback!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.