Join Discord
✨ Try the Model for Free! ✨
I’m hosting my model on SocialDiff.net—a project I’m developing in my spare time. ADetailer is fully integrated, making your experience even smoother.
💖 Show Your Support! 💖
If you enjoy the model, don’t forget to leave a like and a review—your feedback helps improve the project! Also, support the talented creators publishing their work with this model by giving them some well-deserved appreciation.
🌟 Digging my way to the Illustrious Checkpoint. 🌟
Why Illustrious?
• Exceptional Attention to Detail: Every aspect is thoughtfully refined.
• Beautifully Detailed Bodies: Impressive proportions and structure.
• Perfectly Crafted Hands: No awkward poses or inconsistencies.
• Illustrious Vision for Semi-Realistic Results: A balance between realism and artistic finesse.
Key Settings
• Sampler: Euler a
• Steps: 25
Tags to Highlight Quality
masterpiece, best quality, amazing quality, very aesthetic, detailed eyes, perfect eyes, realistic eyes
Additional Enhancements
• All images are polished using ADetailer (face_yolov8s) for flawless face results.
Description
FAQ
Comments (43)
my fav model, very amazing!!
This is a peak model
What external generator are people using to get those giggling bobba videos?
Wan2.1, or Hunyuan/FramePack
My fav IL model
love this model, but does anyone else get random noise sometimes on certain prompts? Like I'll use a prompt, works fine, adjust prompt, then goes to random noise, adjust prompt again, no more random noise? There's no major syntax issues that should cause this
Edit: Solved issue in comment reply, see the issue described here:
https://github.com/hako-mikan/sd-webui-prevent-artifact
hey, are you using same seed on every gen?
also an example would be great :)
Just the same sometimes.
Yes, same seed, but slightly different prompt. Е.g., original one: "..., small perky breasts,...", and updated version: "..., meduim perky breasts,...".
I'll make an example, as soon as will be near my PC.
No not on every gen, but I solved the issue, the issue is described here:
Adjust prompt and emphasis can result in random noise output. I don't think this is unique to your model.
https://github.com/hako-mikan/sd-webui-prevent-artifact
You should be able to solve it without installing it via the "no norm" setting in forge which is what I use.
In Web-UI version 1.8.0 and the latest version of Forge, the same functionality is implemented in the core system, so it's recommended to use that instead. If the core settings include options like the following, it means the core supports it:
Enable emphasis (for AUTOMATIC1111)
Emphasis mode (for Forge) Setting these to "No norm" will achieve the same effect as activating this extension.
My favorite model so far! 🥰🥰🥰
This is far and away my favorite model, thank you so much for putting it out there! You are a hero! You are a river to your people! I am still in awe that my basic ass midrange comp can generate beautiful images OFFLINE no. We live in the future.
🥰 v6:
1. Does well with "landscape" (21:9)
2. Watermark-free (maybe 1/100 images, but not sure - about that 1/one, as I change checkpoints frequently)
3. Does well with (sfw) clothing, (nsfw) nudity, and (skimpy) partial clothing and see-through clothings
I like the realistic style of v5.5 so much that I can't move to v6...
Can anyone tell me which version is the best so far?
Hello, please tell me, what resolution is the best for generation? And does Hires.fix work normally on this model?
I keep coming back to this model, it's just great and reliable.
i have black screen!!!!
what should i do ?
fav model ever, whats been changed on v6?
Out of all the versions from 1-6, there is that distinct sweet aesthetic essence in v2.0 and v3.0 that I love the most.
Great fast checkpoint, RTX 4060 16 gb, generates quite fast. Most of the generation is great quality. Respect!
Lol! What takes a long time to gen up on a card like that? Even Flax works fine on it.
i also have a 4060 with the 16GB, bought it specifically for budget diffusers generation. One of the smartest, cost-conscious PC part purchases I've ever made.
but breaker, just to help you out a bit: this model, ILustMix, is just a standard SDXL (albeit with the backing of the extensive Illustrious training). It's not merged with the turbo or lightning or hyper or DMD2 or any of the various speed-up mechanisms that have been tossed about. Which means that your comment about "generates quite fast" is irrelevant with respect to the model. Your generation speed will be the EXACT same with any standard SDXL model. And i mean EXACT. I just want help you understand that any generation speed variations you're experiencing aren't coming from the model - most likely it's coming from your choice of sampler, that's the usual spot.
My words don't carry much weight as I'm new here. But I'm the more impressed and thank you very much. Keep up the awesome work on the path of light! ;-)
What happened? Why is it no longer available? 😡
Forgot to place the bid unfortunately :(
@GZees Ouch...
how do we get it back?
@johnthewizard1975 i've placed a bid, but it will be available in a week
Definitely a go-to model for me when I want consistently good results. Fantastic work.
My No1 model. Great results, consistent. Use if you like not having 3 headed 5 eyed results!
The best model ever)
My reset. My go-to. My compass. Tried and true checkpoint. 👍
I tried this version and https://civitai.com/models/1560668?modelVersionId=1766052 the looked the same. Ill post a photo for you to see.
probably he made a merge or something
@GZees ok just wanted you to know.
This is the best IL model I've found so far. Expressive and responsive, nice default style.
I really LOVE the near realism I can get with the v5.5 model, but it really struggles with crossed eyes. Is that just my setup or what?!? v6 of this model is also fantastic - the eyes improved markedly - but it lost some of the realism and I miss it.
Totally agree, V6 is fantastic and a clear improvement overall, but when it comes to semi-realistic style v5.5 actually surpasses V6. Otherwise V6 is perfect.
@_Maximus_ I'm very hopeful for v7 to bring back the semi-realism without losing the improvements from v6!
It's been working very well for me, thanks.
Best checkpoint. Always delivers.
I made a Queen out of this model, V5.5 judge for yourself: https://civitai.com/images/81435390
So good for porn much much better than Pony
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.