ZIT-ZEUS-DARKMOP YARA "New Engine"
Detailers or Lora's are not really needed.
res_2 - beta 8 Steps / res_2s - bong_tangent / er_sde - sigmoid_offset / ipndm -. beta / euler - beta (10 Steps)ZIT-ZEUS-DARKMOP SIX-ONE (6.1) (reup)
Please be so kind as to let me know if anything doesn't work or could be improved—I'll fix it in the next version :)
A Simple Workflow for DARKMOP: HERE
DARKMOP XL (FP8) Version INFO!!! FP16 OK :)
Users with a 5950X CPU should not run this; your Core 3 may have failed—unfortunately, this is a known issue with the Ryzen 5000 series. (applies only to the FP8 version)
This version is more or less a test run. I liked some of the results it produced with 12 steps using the “ipndm - beta” sampler, or “ipndm - sgm_uniform.” The model is inspired by raw, vintage, and analog photography. There may well still be some bugs in it; I was only able to test the model myself with 3 images (FP8) before my Ryzen threw a Core 3 error. The FP16 version runs without any issues. However, it may also contain bugs. USERS with a 5950X CPU dINFO & SETTINGS:
Online Generation: I have noticed that online generators using the “Euler” sampler do not always achieve the results that this model is actually capable of. My recommendation for the sampler, fast and good details: “er_sde - sigmoid_offset.” Unfortunately, not all online generators offer this combination. ANIFAN Version: Anime & Fantasy
Trigger: (Anime) (Illustration) (test it ;) )
(euler - simple / er_sde - sigmoid_offset 8 Steps CFG: 1.0)V6 = DARKMOP 6 (AIO) Version
V6 AIO Sampler: dpmpp2m - beta 7 - 10 Steps / CFG 1.0 - 1.5
(Place here: \ComfyUI\models\checkpoints\)V5 = SIMBA (Other Series) ((You can find it on my profile under “Models”))
V4 = MopPhoria Realistic and authentic (Better Skin, Similar to Qwen Hyphoria)
V3 = VMH Realistic and authentic (Similar to Qwen Hyphoria)
V2 =DarkMop Real and fantasy / (more Fantasy)
V1 = All-rounder (Successor to my ZIT-ZEUS-ONE model)
MOP = "Moody or Pervy" XD (not "Mixture of Perverts") from GBRX
We classify this model as an all-rounder ;)
We all know that some details can only be improved with LoRa.
All sample images for this checkpoint were created without LoRa. (Sampler settings er_sde - simple 8 steps, cfg 1.0)
Feel free to put it through its paces ;)
V6 Sampler Settings:
dpmpp2m - beta / 7 Steps / CFG 1.0 - CFG 1.5)
V3 & V4 Sampler Settings:
Samplers Normal: 8 Steps
Euler simple (Speed)
ddim beta (Speed good)
er_sde simple (realistic more Details) (perfect)
er_sde sigmoid_offset (realistic more Details)
er_sde kl_optimal (Nice Colors ;) )
dpmpp_2m_sde beta (Less skin texture)
dpmpp_2m_sde simple (more Less skin texture)
Samplers: Medium / High Q. 8 Steps
res_5s beta57
Samplers 4 Play XD (8 Steps)
res_2s sigmoid_offset
Samplers: High Quality 8 Steps
res_2s bong_tangent
res_3s bong_tangent
res_5s bong_tangentLet me know which settings gave you the best results.
Description
V2 More Details, Improved stability
FAQ
Comments (6)
I'm finding something odd. Across various prompts that I tested, the Yara2 model seems to produce pixel-for-pixel identical results to unstablebastard v5.0. The models have different sizes though. A bit of a head scratcher.
I don't think that's difficult these days, because everyone just takes an existing checkpoint and merges it.
Especially since I think that u v5 has incorporated some of the same LORAs that I use. So it’s quite possible that my merge responds to the same structure as the unstable CPK, but that might just be the case right now; it will change soon since I’ve found a new technique that can do far more than the simple merge or DIT layer merge :)
@zyxt99565 One more thing: all my checkpoints are based on my first DarkMop, so it’s quite possible that DarkMop is included in unstable and other merges (it might be, but it doesn’t have to be). Even if it is, I don’t care—I like his work.
You both do great work. I just found it strange they would produce identical outputs. My experience is mainly with SDXL, where even merging in a lora seems to change the output of every image in some way. I haven't tried merging any z-image models or loras yet, so not sure how it affects the output. I download a lot of models and throw a variety of prompts at them, then keep the ones I like best. But since it is rarely stated what loras or models anyone uses in their merges, its hard to know what to prompt for to find differences between models, or even what each model excels at. Anyway, thanks for the response, and for providing great models!
YARA V2 Is just amazing when I get some free time from working RL I will generate with it, but from testing so far WOW! great work!
YARA for me is much more better, than Six-One.