Want to get acces to all current and future early acces models, request a model or just support me?
Comissions open on http://www.fiverr.com/s/gD2zEyX and https://ko-fi.com/renaissancegremlin
Here is my Patreon from 5$ supporter tier allow acces to ALL models that get posed with early acces: https://www.patreon.com/c/RenaissanceGremlin
My socials:
YouTube
DISCORD SERVER
Twitter FB
My loras are available from my official accounts on:
Tensor Art: https://tensor.art/u/836328663648595213
CivitAI: https://civarchive.com/user/Shrekman17
Seeart: https://www.seaart.ai/user/ab14b528c289f390e228b8c5d6f497f1?u_code=DAS7ETBY
If You see this on any other site, that mean the one that posted the model scraped model Civit and was too stupid/lazy do remove that part
Description
FAQ
Comments (3)
Would you consider doing something like an overhead swing from the side? I've found it hard to prompt. Thanks for this and other models.
After i'm done with more concept type versions for this i probably gonna make versions that are focused on specific poses, tag "dynamic pose" is so badly applied on danboru (that IL has most of data from) that it needs loras to fix this.
GPT is quite good in replication of poses, so if this lora will be popular enough it can be done for sure
Another alternative is, if you see an image with a pose you want to reproduce, use ControlNet to read the pose or perhaps read depth + outline combo from it. This of course is more involved than just dropping in a lora loader node.