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 (19)
Edit: Its up! =D
Update for Illustrious Checkpoint should be ready in the next hours. Stay tuned! ;)
搞R18非常厉害！好多姿势和play别的illustrious模型根本跑不出来，加lora都跑不出来。但是这个模型却没问题！
谢谢!
suitable for pony model as well, some model's only position for my tags are man holding his penis, and unfortunately his penis is deformed and not continuous because of his holding. While this model render a fantastic pose. 对pony也一样，有些模型出来的图片里的动作只有男人手持武器，而讽刺的是他的武器因为他手持的姿势而变形而且不连续可导了。然而这个模型能够出来非常性感的姿势。
Impressive model, i'musing it actively
This model is so good. Even I can make it work. Truly idiot proof. 👍
I've been using it a bit, but it seems that Lora is less effective on Illustrious v.2 than on the first version.
Great Checkpoint, loving it so far! I've encountered a few hiccups, however. So far I've been experiencing an issue with consistent eye color. Particularly for brown eyes.
Ah! The bane of my existence! Trying to make the AI give consistent reliable results! lol
Try something simple like changing the Sampling method used. I noticed you use primarily 'Euler a'. Try using samplers from the 'DPM++' family. Use 'DPM++ 2M SDE' or 'DPM++ 3M SDE' if you can.
What adetailer do you use? Having problems with the eyes being blurry or bleeding? All your images have amazing eyes. Using your checkpoint, pos/neg prompts, smooth detailer booster lora, lighting lora, and the upscaler you recommened.
Overall great model! The fingers I can tweak but eyes I haven't a clue.
Weird. I never had any problems with adetailer. I use the standards 'face_yolov8n.pt' or 'face_yolov8s.pt'.
Inpaint mask blur around 6~8. Inpaint denoising strength 0.2~0.3.
Post some images you are having problems with the eyes so I can check them out.
@Qvoheu oh I meant until I figured out how to add the face detailers the eyes, and hands would be wonky. But figured it out and some pics are pre-adetailer, and the good ones are with eyes-hands adetailer.
Great model, gonna try some other characters, and scenes when I get home.
mind sharing your settings for hands and eyes?
@Qvoheu You should post these settings in your description. You should also pin this comment if you can.
Good model. But! Mb someone can explain me? The longer and detailed the prompt, than more cartoonish the image becomes. At least in my case. It's ok something at 100 tokens, but closer to 200 or above... I can fix it with some LoRAs, but can't get why it so dramatically changes.
the results of one prompt are similar, do not change much with seed.
I think it needs an update, denoising makes my images worse even with low strenght with hiresfix
Please try the new version and see if there are any changes! =)
Remove all space from your Smooth Embeddings file names or not working.