Update v2: tripled dataset + completely new captioning,
Should be working ok now (doesn't mean it won't produce bad anatomy some of the time, but for me at least it's useable now)
The model knows some gags and has a lot of variety in perspectives.
Often doesn't play well with other (concept-) lora, mix them in with care.
tested with flux1dev + acornisspinning
i recommend a wide or square aspect ratio.
V1:
I'll just leave this here. It's highly inconsistent and i highly recommend using the pony version instead.
If you insist on using this one, try to write a prompt excruciatingly detailed and be prepared for wasted time on failed generations.
training notes v1:
cogvlm - one sentence + danbooru tags.
3000 Steps
lr 0.0001
dim alpha 16/16
Description
FAQ
Comments (2)
I want to recommend this concept of Lora. Even though I have created a version about SD1.5, I still think it is not perfect enough
I just spent a whole day trying to render a simple woman lying down on her stomach with her feet put up. Tried all kinds of techniques to fix using the same seed, and it all failed. This was the one thing/lora that worked!! Only had to use a weight of 32% or so. What a life saver!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.