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 (38)
Great! The new version has been released. So, are there any notable changes in version 1.5 compared to the previous version?
I'd like to know that too. want to spend the 1k to get early access but, I want to know whats different
I personally like v1.0 more than v1.5.
Background: v1.5 is slightly better than v1.0, but not much differences.
Color: v1.5 is a bit darker/gray-ish which is a bit similar to Oblivious Mix
Noted. Anyways already working on a version that will give similar style to the original prefect pony
What version of Illustrious is 1.5 based on ?
I hope it's not 0.1 anymore
Aren't 1.0 and 2.0 generally considered worse than 0.1 anyway?
@HaomingGaming I tried illustrious 2.0 and it's great. In what way it's worse?
Great model. I want to know if the new model add new charactor?
good
Is it based on Illustrious 2.0 or that update?
could you share ur hiresfix settings ? like do u add steps how much denoising and do u adjust cfg scale on denoising as well ?
u can very easily find that out by just dragging any of his showcase images into your webui
the model only has images tagged "bara" in its sample gallery, which means whole model is hidden from users who have that tag blacklisted
i try it
nice
Very good model, although I still prefer 1.0. For me, mostly, 1.5 just fights me too much with inpainting. It keeps changing colors and patterns even at lowest denoising levels. 1.0 is also incredibly sensitive, but its far easier to work with.
Using 1.0 I was able to generate a lot of content easier. I am not sure what 1.5 improves other than very specific areas. For me, everything else was unfortunately lost. Futa in 1.0 look better, meanwhile they all look the same in 1.5, It's a shame really... I am also not able to tell if it's picking up artist styles like 1.0 did.
Donate cocksuckas!!!
Disappointed in 1.5 version. The model has gotten worse. The detail has become less, the color has dropped. I'm not happy with the result. Comparing with the previous version, this one wins only in the generation of fingers and hands, but not everywhere. Perhaps it's the way the loras works with the new version, but I really doubt it.
This is Art
After some tests, I switched to version 1.5. It's less "oily", less blurry and moves more towards 2D, unlike version 1.0. So v1.5 is definitely an upgrade (in my opinion).
引き続きテストしていますが、個人的にはかなり残念です… 2.0に期待しています！
Sorry, what "I had ENSD: 31337 all of them" means ?
It is a setting within stable diffusion or other ui's called 'Eta noise seed delta' that effects Eular A and other ancestral samplers. All it does is make seeds consistent across different generators to make the same image. 31337 is just a popular choice that people tend to use. Hope that helps!
@soup any article or anything explanation about that?
@DTdota2 Not any I know of, I have just been using stable diffusion long enough to know that people have used either 31337 to replicate novel ai when things started developing or they just leave it blank due to it only being for seed consistency.
I think the v1 version is better, I hope v2 is the comeback
V1.5 is good. Very versatile even more than V1 people say a small drop in quality i dont mind it this version smarter with loras and concepts.
I for sure like V1 better, the style is what does it for me.
I prefer the style of v1
看起来就十分的不错
Good
66666666666
.
Very solid
Some thing awesome
Cult of Gremmy Approved
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.