FLUX version just released! Don't hesitate to share your best images on this page, thanks!!!
The version PONY V2 fixes some problems and help getting more consistent and relevant images. Next step will be choosing relevantly the numérique of steps. Here, most trzined images had 6 steps or 9 steps.
Use it at weight 0.8 to 1.2 or experiment anything else (and tell me if it works, so that I could share). I use Euler A or DDIM for this one.
I'm proud to propose this first step aimed to generate step by step drawing guides.
For v2 and for FLUX: triggers: "howtodraw", "x steps", and then, the things you want to describe, "greyscale" or "colored final touch" if you want, then the style and so on.
For v1: The main triggers are "drawing of a (subject) in (x) steps", "sketch tutorial " , "step by step guide".
It is the first version, it won't be sufficiently accurate because it has been trained with 3 to 10 steps drawing sheets and I think it's too complicated to have a so good model with it. I made it as a proof of concept.
Description
Trained with more stable dataset
FAQ
Comments (11)
I guess one of the "Pick up a pencil" twitter freaks made a lora lmao
"AI is a tool" wink wink!
Actually useful AI :o 👍
I've been wondering if something like this would ever exist.
Ngl i can even learn drawing with this. Thank you kind sir for creating this.
Finally, everyone can make useless drawing tutorials now, with a bunch of circles and pretentious guidelines!
This is so fun! Love it ♥
Holy hell,,this is actually actually extremely useful. Could you do a loomis head one?
a very interesting lora, sometimes it works, sometimes it does not. it's wired, i used the sample img's prompt as input, in most of situations, i couldn't get what i wanted.
any plans for update?
A more fine tuned version, especially with detailed mannequin skeleton guidelines, and detailed head guide lines would be amazing.