Make sure to leave a bid on your favorite version: https://civarchive.com/auctions
Every bit of buzz counts!
=============================================
UPDATE: SmoothMix Illustrious 2XL +NoobAI v2
Can now reliably create very high quality images with low as 15 steps and 1.5 weights! Check the showcase for the images steps and weight used.
The Showcase have images created using Stable Diffusion Forge and ComfyUI, using both of my workflows.
Addressed a few of the issues learned from feedback. (Thank you again. These helps alot!)
Main issues:
Men are hard to make - Ok, so, since my focus in on the lovely ladies I must confess I neglected to check if men were actually possible to make lol. It should be much easier now.
The night and dark places are not dark enough - I'm trying to avoid the issue of oversaturation but I guess I went a little to far. Prompts that affect low ilumination like dark room, low light, dim light, should have stronger effects now. Increase their weight if you find it necessary: (dark room:1.5) like so.
Smooth Worksflow creates images that look very different from CivitAI with same prompt - This is addressed on a new Workflow version. Go check it out!
=============================================
SmoothMix Illustrious 2XL +NoobAI
Merge of Smooth Mix NoobAI with the new Illustrious 2 XL.
Very versatile and allows for a wide variety of styles!
More poses were added! Try to be as creative as possible!
Higher quality on faces without Adetailer!
Both Smooth Embeddings for NoobAI or Illustrious work well! Use your favorite!
=============================================
Smooth Mix is also available on Tensor.art: https://tensor.art/u/836729543011162095
=============================================
SmoothMix!!
All my Illustrious Loras/Embeddings are compatible with NoobAI Checkpoints! Make sure to change your settings if you are using the CivitAI Site Generation!
When selecting Loras/Embeddings, go to this option:
And change it to Advanced Mode!

Recommended settings:
Steps: 15 ~ 30 - (Euler a/DPM++ 2M) - CFG: 1.5 ~ 3.5
Steps: 25 ~ 40 - (Euler a/DPM++ 2M) - CFG: 2.5 ~ 5
Adetailer
Hires. fix: Remacri
Use the set of Smooth Embeddings! The Positive and Negative Embedding will ensure a high quality image! No multiple quality prompts necessary!
Use Smooth Detailer Booster for better effects and details.
Use Smooth Lighting Enhancer for better lighting effects!
Now go and have fun!
Description
FAQ
Comments (22)
Edit: Its up! Checkpoint should be available for site generation soon! =D
Get ready everyone! Big update in a few minutes! ;)
For those waiting to use v.3 here are some good news from the mods:
"(...) early next week we'll be rolling out full generation coverage, all checkpoints (including all versions) will be supported for generation."
So every version of SmoothMix will be available for Site generation!
Finally
I'm either doing something wrong, or this model is overtrained on camera angles from below with the character leaning back with their palms on a surface behind them, fingers away from the body. I can't seem to get away from this behavior, even with negatives. Something as basic as getting a shot from eye level is next to impossible in my tests so far, and the model will go to ridiculous lengths to place a surface behind the character for them to lean on. I'm going to experiment more, but this is seriously annoying, coming from other Illustrious models.
Any tips to avoid these behaviors would be welcomed with open arms.
I have the opposite problem, where as soon as I type 'bedroom' into the positive prompt, it goes high camera angle, which I flipping hate, even when I put "High camera angle" in the negative prompt at strength 5.
@zon14 The booru prompt to avoid that should "from above". Try putting that in negative weights. How strong this is depends on the specific model. The biggest camera problem beyond what I mentioned in my comment above is that most Illustrious models seem to insist on posing solo characters in the straight-on angle ("straight-on" is another booru tag), even if you put it in the negative prompt and add booru tags like "three quarter view" in the positive prompt. All these models are somewhat quirky, but I just found this one to be quirkier than most in an obnoxious way.
@RiseKujikawa Yeah, I remembered the 'from above' tag after I posted that. Straight-on I'll have to give a try.
Why do the characters I generate have overly realistic faces instead of matching the example images' style?
+1. Feeling mislead here
What!? o.O I can literally remix any of my images and not get any overly realistic faces. Even with prompts like "ultra realistic". How in the AI Gods name are you guys doing that!?
Same problem, can't reproduce the sample images even with the same copypasted parameters and exact embeddings. Everything looks dark, western and shiny.
...just how? :D
Show some results with the generation data, plz.
This checkpoint hops across styles pretty easily.
Hi, this looks amazing! I just want to ask, anyidea on how to replicate your results in comfyUI? I tried but I am getting not so good results. Do you know what scheduler should we use?
this checkpoint is incredible
The Kling img2vid engine absolutely adores images made with this checkpoint. I've had mixed success animating pure cartoon/anime checkpoint stuff, but this one works great.
Well, my guess is that this is a semi-realistic checkpoint with realistic shadows, and Kling with similar stuff are mostly trained on IRL videos.
Based on Illustrious 0.1 or 1.0
Well, HF page says just Illustrious.
https://huggingface.co/Laxhar/noobai-XL-1.1
will you also do Noobai checkpoint like this version ?
Yes! ;)
@Qvoheu cant wait :)
All Checkpoints are available for the Site Generator! Which one is your favorite? Have fun!!
Details
Files
smoothMixOldVerNoobai_illustriousV3.safetensors
Mirrors
smoothMixOldVerNoobai_illustriousV3.safetensors
smoothMixNoobai_illustriousV3.safetensors
smoothMixIllustrious_illustriousV3.safetensors
smoothMixIllustrious_illustriousV3.safetensors
smoothMixIllustrious_illustriousV3.safetensors
smoothMixIllustrious_illustriousV3.safetensors
smoothMixNoobai_illustriousV3.safetensors
illV3.safetensors







