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
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
This is a Anime / Fantasy CPK
This version has 6 Lora's baked in. It reacts to swords and anime. If you test it, you'll find out :D
We mustn't forget that ZIT can also create normal images, so don't forget to mention what you want to create before your prompt :)
FAQ
Comments (19)
The V1 is a really good checkpoint. Nice color and contrast, very good realism and good prompt understanding. Thanks for it, i like it :)
I'm glad the checkpoint actually responds to simple inputs, nothing complicated.
Just started to test this model, going through the recommended Sampling/scheduling pairs. Euler/Simple and ER SDE/Simple worked well, while for me the DDIM/Beta became very artifact heavy and grainy. Seems very good so far.
With or without Lora? I noticed this with ddim - beta. As soon as Lora comes into play, it goes haywire.
No Lora's. Not even tested any ZIT checkpoint with a ZIT Lora yet, just SDXL ones (but not with yours). Might be that it does things differently since I use Forge Neo instead of Comfy.
This is really a great model. I hope an FP8 version will be released in the future. This is very important to me, as I only have a 16GB consumer-grade graphics card.
This model runs on a 4070 12GB VRAM Card :D
I have a 3060 12gb and run the FP16 models all the time on ZIT. Every bit of information I read says I can't but... I can and it's quick!
@pedro1148393387 Maybe it's because I have an AMD 9070xt graphics card and my running FP16 will be very slow. Only when I use the FP8 model will this time be reduced to about 40 seconds.
@xl1627658896589 You can set the loader to run it as FP8. Set the load clip from device to CPU to give your graphics card a break.
rtx2060 <
Nice job. My favorite zit model so far
I tested Phoria V4 and can only say... wow... very impressive. With er_sde/simple 8Steps produces images with excellent color and contrast. The prompts I use are implemented very well. Ich liebe es, danke für den Checkpoint :)
Thanks a lot for the feedback, Gorean! Really happy to hear Phoria V4 is hitting the spot for you – excellent color/contrast at er_sde/simple 8 steps is exactly the sweet spot I tuned it for. Glad the prompts are coming through clean and strong too. Means a lot that you love it! ❤️
V5 is coming March 18, 2025 – gonna push the pores, consistency and raw realism even further. Stay tuned, and if you got any favorite prompts or ideas you want to see in V5, drop 'em here! Appreciate you testing and writing this up.
@zeus_onl I'm looking forward to V5 :) I currently have 104 different prompts to test, all of which depict something different, but there isn't one I would consider my favorite. Here's a prompt that I think offers a lot of overall testing that interests me (realism, color, contrast, skin, eyes, hair, latex, spandex, collar, execution...)
photograph of a 21 years young slavic woman with platinum blonde long ponytail and side locks. She have aqua-blue eyes and bold graphic long winged eyeliner. her neck is with a Small but very tight-fitting metal choker with an O-ring that hangs downwards. She also wears thin hoop earrings. She's wearing a bright white very shiny ((onepiece latex crop hoodie)) with drawstring for the hood. The drawstrings are neon pink. The hoodie has bright neon details at the hem. she is wearing a smooth and thick shocking pink spandex mouthmask that ((covers her mouth and nose completely)).
The skin and the lighting are very realistic. The image is very detailed, especially the woman in focus and her clothing and the fabric of her clothes. the background also contains many details.
Would love a no AIO version of DARKMOP v6
DarkMop V6 Diffusion Model coming soon :)
I tested V6 AIO, it do what it should do (Because the previous versions were already incredibly good) and it do it very well :) i used er_sde/beta 8 Steps and the pictures are very beautiful and the images are almost flawless. Ich danke dir für den Checkpoint, ich liebe es :)
AMAZING!!!!!!!!!!! Best version yet....this is as close to perfection as it comes. Excellent prompt adherence, quality, skin details...well done!!!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.