Hey guys and gals!
No EA this time, BUT 👇
I encourage you to post at least one image after downloading my model.
Just 150+ postings will compensate training costs at CivitAI. You can also collect this model or interact with my images. This is just a TIME for you but IS A GOLD to me.
BLUE BUZZ is the only thing required to make new trained model ;)
I don't ask you to donate YELLOW BUZZ, but will be very glad if you spare some. No matter what, all my BUZZ will be spent inside CivitAI on training new models.
TL;DR; Combination of creative visuals and sharpness of CinPony v2 with Booru / Natural language prompt adherence from Illustrious models. Feel free to post flawy examples and comparisons. I'm open for critics as usual.
[DISCLOSURE] I am using the Post-Maker (3-pass workflow) to produce HQ images using only the released model. You can download it and modify the Steps or resolutions. Steps 30 for 1st pass and 8-10 steps for 2nd and 3rd passes are enough to produce good results 90% of tries. 3rd pass is not so important.
V2 Highlights
RE-balnced colors toward true color natural palette
Sharper render - more small details
More natural expressions, poses and environment textures / geometry
Better lighting
Wider CFG range (CFG 7 == realism)
V1 Highlights
<TBD>
Description
My first Illustrious release.
Sharpness and creativeness of CinPony v2 Razor. Prompt adherence of Illustrious models.
CFG 3...5 and Clip Skip 1 for realism. Clips Skip 2 also works.
Euler + Beta gives optimal combinations of Quality and Speed.
FAQ
Comments (7)
Brilliant!
I'm still training. Hope in few days will be ready for new update.
Looking good so far, the prompt adherence is very good, the only problems I'm noticing is some deformities in the teeth,eyes and nipples
Thanks for feedback. I usually go with 2- or 3-pass workflow. This fixes the eyes and other smaller shapes.
I see SDXL in general struggles to produce good fingers and eyes at first run if it is oriented to realism (too much details to pay attention to at first run).
Seems like next thing to work on is detailing of face and hands. I need to learn how to do masked training.
I would be glad if you post some examples... 🙏
@homoludens done🫡
@homoludens that would be good, for a V1 looks very good, already better prompt adherence that some models
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.