👇👀 Read me! 👇👀
This is a slider for IllustriousXL trained on the base model Illustrious XL v0.1. The training data for this slider is the same as my popular detail slider for PonyXL, so there is a little style bleed but nothing you can't overcome with a style LoRA. The goal of this slider is to easily and consistently introduce more detail in generated images, mostly in the background.
No activation tag. This slider LoRA supports bipolar input weights, although negative input weights are not as consistent as I would like in v1.0 . I recommend using weights 3 to 4.5 to add a nice amount of detail to your generated images.
It is important to note that if you're getting weird messed up backgrounds, you should set your Hires. fix "Hires CFG Scale" to anywhere between 3 and 5.5 . Personally I tend to stick to 3.5 or 4. And you should use sampling CFG Scale values <= 7 generally speaking.
Example prompts can be seen in the attached example images.
No special negative prompting needed, although the scenery tag is great to add for any scene that is outside.
Base IllustriousXL does a pretty good job at adding details when you use the correct prompts for them, so this slider LoRA isn't as necessary to use as it is for PonyXL, but it still provides an easy and consistent way to add details to images.
If you generate images with this, please share! I love seeing what people make with my LoRAs and it helps keep me motivated to make more. If you have IllustriousXL LoRA requests, feel free to leave a comment and I'll look into into it 👍
Known Issues:
Negative weight values do not consistently remove image detail
The LoRA somewhat stylizes output images
High positive input weight values (
5>=) make backgrounds fall apart at higher CFG Scale values
Changelog:
December 2, 2024 - Initial release
Description
v1.0 Initial Release
FAQ
Comments (15)
Will you make an illustrious version of the age slider?
@crazymanjj Yes, currently working on it. I hope to have it released by the end of the weekend,
Does what it says. Its not as noticeable as other detailer loras like the ones ill link, but depending on what you wanna do it could already do enough.
Ive tested with following model by itself, and also with these loras:
https://civitai.com/models/827184/wai-nsfw-illustrious-sdxl
https://civitai.com/models/99619/control-lora-collection
https://civitai.com/models/510261/spo-sdxl4k-p10eplorawebui
Those other 2 loras are more extreme, and just using those might already give you enough results, but i tried this one just to test, and even tho i cant exactly describe what i think it added, i just seem to like the composition of images better when this is used too, so there is that. Might be different for you, anywhere from "This doesnt do much" to "This does too much".
@Bigboyblaziken Thank you for your comprehensive review! Compared to PonyXL, IllustriousXl based models seem to do better with detailing out of the box, so a detail slider doesn't have as much impact in IllustriousXL models (at least from my testing). I also noticed that this slider seems to make compositions a bit more cohesive and sometime better prompt-adherent, which honestly surprised me as I didn't make this slider with that goal specifically, but it's a welcome addition nonetheless.
@Shed_The_Skin Hi, youre welcome. Yeah IL seems pretty good so far, at least WAIs one. This one does still add even more details, just not as extreme as those specific other 2. Which sometimes might be better for some people that dont want too much.
I really liked Pony version of it but that one changed style sometimes and break when used with multiple other LORAs. Hopefully this one will be as good or better. Will edit after i try it enough times
@Wizzi I'm glad you're giving this version a try. If you come across repeatable issues with this LoRA, feel free to send me a DM and I will look into fixing those issues if I can :)
@Shed_The_Skin after trying it for a few days i reached to similar conclusions with the other comment by blaziken. It doesnt have much drastic changes but also not much downsides. Pro is slightly more details, Con is i feel like genitals look a bit worse in NSFW gens.
@Wizzi This has largely been my experience as well, but I will add that it also seems to make backgrounds a bit more coherent. I don't get as many oddities and non-sensical geometries in the background as much when I use this LoRA.
it just works!
any chance you will release a v2?
Good!
it wont show up on my lora list on the forge webui after putting it in the lora folder?
@gaara675
Ensure in Forge's settings you have this setting enabled: "Always show all networks on the Lora page (otherwise, those detected as for incompatible version of Stable Diffusion will be hidden)"
@Shed_The_Skin ok thanks
Details
Files
StS-Illustrious-Detail-Slider-v1.0.safetensors
Mirrors
StS-Illustrious-Detail-Slider-v1.0.safetensors
StS-Illustrious-Detail-Slider-v1.0.safetensors
StS-Illustrious-Detail-Slider-v1.0.safetensors
StS-Illustrious-Detail-Slider-v1.0.safetensors
StS-Illustrious-Detail-Slider-v1.0.safetensors
StS-Illustrious-Detail-Slider-v1.0.safetensors
24-Detail-Slider.safetensors
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.


