These are my Mergestein realistic experimental models, a lot of merges merged in a merge to make a merge. Works for anime/toon/game/real life characters and can do furry too.
on-site generation with "private" NSFW support:
Uncanny v2 (shows as uncanny-)
If you want to support me, just upload an image on the model page, it doesn't matter if is good or not, i receive blue buzz for LoRa training.
The images i upload on the model are generated using Euler Beta and without any LoRA, CFG Rescale, Hiresfix, ADetailer or Upscale. So, the quality can be improved. Like all illustrious models, close distance is perfect, medium is ok and far is ugly.
All models already have a CFG boost merged in the model (it works well with low CFG, use less than 5 CFG), so is not recommended to use any CFG LoRa, you will only get burned images and some detail boost LoRas can affect too, if you still want to use them, use low weights (less than 0.3).
Yes, all models work with NSFW and Age stages works well, so please don't use it for bad things.
Samplers, Schedulers and CFG Recommendations:
The less CFG, more realistic. The more CFG less realistic.
Euler A Normal/simple/SGM Uniform 2.5 CFG (max 5 CFG) if you don't like skin texture (Skin pores, wrinkles, etc)Euler Beta 2.5 CFG (max 4.5 CFG) for better 3d/realism, close to DPM but with much less "noise".DPM++ 2/3/4M SDE Karras 2 CFG (Max 4 CFG, more the CFG = Brighter/burned). More realistic but too noisy and adds too many details.For Euler/Euler A start with 16 steps max 30 steps.For DPM start with 20 steps max 35 steps.Resolution:
Works with all SDXL resolutions, i personally use 1024/1152x1536 and sometimes 1280x1536 (with this you can get body extension).Recommended general base prompts:
Positive:
best quality, masterpiece, excellent, high Resolution, aesthetic, photorealistic, photo backgroundNegative:
worst quality, bad quality, low quality, lowres, low resolution, anatomical nonsense, artistic error, bad anatomy, bad feet, bad hands, extra digits, conjoinedPrompts to get more realism and quality:
(it can reduce character accuracy, recommend using with LoRas or more weight for anime/toon/game characters)
Positive:
best quality, masterpiece, excellent, high Resolution, aesthetic, realistic, photorealistic, photo (medium), photo backgroundNegative:
(Remove "(toon (style), 3d)" for better character prompt follow and creativity)
worst quality, bad quality, low quality, lowres, low resolution, anatomical nonsense, artistic error, bad anatomy, bad feet, bad hands, extra digits, conjoined, (toon (style), 3D), traditional media,Credits to respective creators, i just merged things together (sorry, forgot the realism models and LoRas used on my personal realistic merge, it's old), for my Wai x Janku + NovaMoon-PM ILL XL all credits are available on the model page same as my Uncanny Animu Plus.
Added to Uncanny Realism dark by ntc
Uncanny v2 added Ahegao - Pleasureable Expression by 6__6, as a fix for eyes and mouth (and ahegao looks better too).
Uncanny-A Plus added to the merge PornMaster-Pro noob-v5, CyberRealistic XL - v8.0 a, cfg scale BOOST and NAI vpredfix (0.1 weight strength each one) and uses my Mergestein Animu Plus as base instead of vZero (and still has the aheago LoRa and other NSFW ones).
Description
Used the first version, changed CLIP for a more updated one and merge it a little with my Uncanny Plus version, with this it has better prompt follow, has less contrast for more natural colors and looks a little more realistic (realism and quality depends on the characters used, some look more realistic and with better quality than others).
For some reason it makes images looks like has some type of compression/grain effect even without using film grain prompt, is the same model with just 2 changes, so i don't know how it got it but looks interesting. This effect only shows to me.
Has the same face effect and is due to NoobAI, nothing to do about it unless i remove it or train a model.
Fingers still sometimes can look weird, this can be solved with more negative prompts (Using realistic on positive prompt can do this, so i recommend to test with and without it)
FAQ
Comments (10)
Excellent model that can push pretty close to realism if you prompt it to. Very flexible as well. I like the aesthetic of slight surreal. Looks great.
Uncanny V2 is incredible, one of the best checkpoints I've used, and I've used a lot. Great work.
theese are the best anime-realism models i ahve ever seen, heavent seen better model yet, understands every anime charecter and makes beautiful face and skin, amazing model !! please make more of your stuff!!
Really nice work on this. Uncanny V2 is very good. What is your merge process, if you don't mind me asking?
Nothing special, i just use ComfyUi with simple merge node, as a base i use my merge of anime models with updated database (right now is my Mergestein Reborn model), merge it with a personal realistic merge i did time ago, try a lot of different strength until i get something i like, then i add some LoRas (test with different strength), now i merge CLIP of the models until i get a good result (test with different strength), then merge the model merge, the CLIP merge and an additional model to reduce LoRa strength and stabilize it (test with different strength), and that's all. Most people forget about CLIP and that can change the output a lot.
@Patuwa Thanks for sharing. Agreed on the CLIP. Again, nice work!
Can you make an updated illustrious version
I'm working on one but it will take more time, i want it to look good.
@Patuwa cant wait.
@Patuwa yeah, we are waiting for it bro :)
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.


