Hey there,
Step into Illustrix, my finest creation yet – a carefully crafted checkpoint merged from alot of checkpoints and 24 hand-picked LoRAs. This model brings together vibrant color, insane levels of detail, and remarkably accurate prompt adherence – all while remaining incredibly user-friendly for both beginners and advanced users.
Showcase Settings: 900 X 1600 / 40 Steps / CFG 7 / Clip 2 / Euler A / no Adetailer / no Hi-Res
🎨 What makes this model special:
✔️ Extremely precise prompt response – what you write is what you get.
✔️ Rich, vivid colors – straight from the model, no extra tuning needed.
✔️ High-detail rendering – skin, hair, fabric, lighting – clean and intricate.
✔️ Beginner-friendly – works great even with basic prompts.
✔️ Balanced fusion of style and structure – no overfitting, no artifacts.
Whether you're using simple prompts or crafting complex compositions – Illustrix delivers.
I really hope you enjoy the model — I'm super excited to see what you create with it!
If you like what I do, leaving a like, a comment, or some feedback would be very cool — it keeps me inspired to keep creating! 🖤
You can also follow me for more, or if you’d like to support my coffee addiction ☕ (and my creative madness), you can do so here: https://ko-fi.com/jedas
Check out my Instagram here: https://www.instagram.com/jedasaiart/
Stay awesome, stay healthy — and have an amazing day! ✨😊
Description
FAQ
Comments (6)
It certainly looks good. I'll be downloading it now and checking it out tomorrow.
Cool im curious about the results :)
@Jedas Posted mine. Took me a little bit of time more than I intended due to work and having to wait for my son to be at school for several of them.
As for the model, I do think this is the best one you've done in this style. I really loved Anillustrious and made several personal loras using each version. This one does seem to be more precise with details (though like all models it can get overloaded with too many color tokens) and it follows both natural text and booru tags well.
I made two different runs: one with controlnets and one without. Some of the poses I made tend to be really hard for models to do without butchering the subject (especially the "shushing" and "on one knee" ones) but aside from the model liking to make really thiccccc thighs for the shushing pose, it works with controlnets wonderfully. As for letting it choose the pose, it did a good variety of different poses with the same prompt.
Sadly some of my images are being hidden (without the site telling me why), so that sucks.
Now to remake my personal loras using this one :)
@WoB hey thanks for trying it out so fast then:) and the feedback
@Jedas You're welcome. Happy to try it and give it. I think your models are some of the best on here.
Looks very clean and precise. Can't wait to test it out.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.