If you like my work, drop a 5 review and hit the heart icon. it's free and keeps me motivated
All my models are officially hosted and maintained by me on Tensor.art . use my Exclusive and public model for free on tensor.art
06/06/25 : v2.0p released
Main focus of 2.0b is cleaning the style influence of v1.5
19/02/2025 : On-site Generation added
Private commission on fiverr
Get early access to my upcoming NSFW Lora on my Patreon.
early lora share on discord for patreon.
I was hoping you could support my work by joining any one of them and get early access to all my upcoming loras and other perks, such as fan requests and a Discord role.
Join my Discord Server
check the images for prompts
use lora at 0.7-1
Adetailer for faces
Img2img upscale
4x-ultra sharp
comment you idea or request
Suggested settings:
I had CLIP skip 1 on every image
Samplers : Eular A, DPM++ 2M
CFG : 5-6
I had ENSD: 31337 all of them
All of them had highres.fix or img2img at higher resolution.
I don't use restore faces
I use Adetailer for face details
4x-Ultrasharp upscaler
positive: masterpiece,best quality,amazing quality,absurdres,
negative: bad quality,worst quality,worst detail,sketch,censored,watermark, signature, artist name
Join my Discord Server
Description
FAQ
Comments (34)
A changelog for each update would be nice.
Thank you Goofy_Ai for continuing evolving your wonderful ILXL model :)
Very clean. Great model.
is the file for v8 broken? im getting a "Error getting file"
do you mind letting me know what the advantages of using this over base illustrious is?
none, the author just keeps on rererereleasing for engagement
Compared to the base Illustrious base model (as in Illustrious-XL 0.1 and Illustrious-XL 1.0), this has much better defined style, thus easier to use for certain parts.
Compared to older versions though, there are not a single clear cut on what is improved and what not. Though, when compared to v1, later versions have more prominent style. Often time, how the model precision (to prrompt) and how it works with LoRAs is the differences. (from 3 to 7, LoRA compatibilities are bad, 4 has an improvement, but still).
@EnlightenAIUser don't forget "putting models on early access for an absurd price to farm buzz from people who don't know this"
Very good😁
I just realized I don't think anyone's made a "catching raindrop on tongue" LORA. Can't find much anime art of it either, just IRL images.
V8 is alright, not much of a change from v7 tbh, just maybe a little more detail. though imo the noses look worse.
输入: 非常好用
v3 is best
How so? Isn't it super outdated at this point?
@viviangrace1985392 the subsequent "updates" are less diverse in artstyle. I still use V1 because it's the best at 2.5D
All the other "updates" were much less capable of producing other art-styles.
Very nice
Will you be finetuning the anima model anytime soon?
thank god u can hide content from specific user. the furries spammer at gallery is too much
You can also spread the net wider and hide certain tags , not perfect but gets 95% of said tag.
I'm not sure if you're using ComfyUI in the examples; although it's set to -1 here, when I run the workflow, the image appears black. Obviously, I solved the problem by setting the script to “skip” with -2.
great checkpoint
Currently the best SDXL anime model, featuring aesthetically pleasing, harmonious, and diverse results.
Can someone explain the difference between versions of THIS model and the NSFW version?
Bcs im using a lot of time this model, 6 and 7 versions and cannot realy understand the difference between versions.
But i pretty love this checkpoint!
there's no changelog so the rumor is that the creator makes non-updates to farm engagement and buzz with early access
In my opinion, V1 is superior bc it can do 2.5d much better than the subsequent "updates"
Are you perhaps planning to upload anima as well?
what is difference between versions 7 and version 8?
nothing. he just puts the models on early access to farm buzz
the anime cutoff date isnt' even changed so the "new" models suck
bigger nose
Please do Anima!
Let's see:
No changelog
No advance of anime cutoff date
Put model on early access
Bro wtf are you even doing with these "updates????"
The author is under no obligation to answer to you; if you don't like it, don't use it—it's that simple.
@Gipno goofy kinda is, especially since hes doing early access sales, the least he could do is add a changelog
I think the ""developers"" of these models should always say what they changed, if the anime cut off date changed, what they actually improved on the models
because what is the freaking point otherwise, its beyond annoying having to download most models because the "developers" dont feel like its important to inform their users about what they did that makes it different from all the other checkpoints
specially when the models are put on early access and expect money out of it in return
common decency isnt that hard of a task
then again this is 2026 we are talking about
Hey goofy, can you go back to v5 please?
I'm really looking forward to an ANIMA version being made.
Details
Files
prefectIllustriousXL_v8.safetensors
Mirrors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors
pr3f3ct_U1l1.safetensors
prefectIllustriousXL_v8.safetensors
Prefect illustrious XL.safetensors
Prefect illustrious XL.safetensors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors
prefectIllustriousXL_v8.safetensors








