Stable Virsion: 2.0
Quality Tag:
Anime example: (anime coloring:2.4), close up, face focus, breasts, focus, (masterpiece:1.1), (best quality:1.1), (newest:1.1), (absurdres:1.1), (highres:1.1)
I used the Mikoyan(style) tag during development and submitted samples, so if you add the Mikoyan(style) tag, it may be easier to stabilize the drawing.
I'd like a prompt for model performance testing...
Base model is Hassaku XL (Illustrious)
WIP Now!!
I'll upgrade it gradually to suit my tastes
v1.0 I tried to give the body a three-dimensional feel.
v1.1 Improved lighting and rendering stability
v1.2 Changes to coloring and improved drawing stability with almost no change to the drawing content
v1.3 It wasn't bad, but it didn't seem like it was of a quality worth releasing, so I skipped it.
v1.4 I made some adjustments to make the expression look stronger. The drawing may have become a little easier to break down.
v2.0 Change to manga style
v2.1 Changed to give it texture(Weapon rendering has become unstable
v2.2 I aimed for a more manga-like expression.
v2.0a It was developed based on v1.4 to prevent the pose from collapsing, and v2.2 was used, but since the features unique to the 1.x series have been reduced, the next version may be modified based on 1.4 again.
I've made so many that I don't know what's good anymore
Description
FAQ
Comments (11)
After reading the description (cause I do that), it seems that the numbering discrepancy (out of order) is because version 1.x is 3D, and version 2.x is more manga-ish? Despite version 2.x was released earlier, but now there's a 1.5. I ask because it seems 1.5 isn't mentioned in any of the notes yet, as far as I see. Or was it just a miss-type and supposed to be 2.5? The more I look, the more it seems my initial assumption was incorrect and it was supposed to be version 2.5?
Developed based on 1.4, added corrections to make poses that were prone to collapse in 1.4 less likely to collapse, and named it 1.5 as the successor to 1.4. However, as you pointed out, it is true that the shadow expression in the output is closer to the 2.x series, and as a result it feels like the 3D feel is lost.
@GrayColor Thanks for the clarification.
Amazing, although both versions are based on the same model, they have distinct characteristics. I think I will keep both versions.
Your Model, My thanks
https://civitai.com/images/74218532
Btw, without your model, maybe 500 even more image couldnt be here right now, check my bio and see what you participate to create.
the 1.4 is at my opinion one of the most accomplished model
I've noticed that you using Hyper CFG-1 low steps lora in preview images, can you make separate version of the checkpoin with this lora merged in? that would be highly appreciated, because i can save ram during loading, also i've heard that merged lora works better than external one, i don't know if it's true.
Yes, but what version do you need?
@GrayColor this is totally up to you, but i like 1.4, very clean style and not so vibrant and plastic colors, also i don't know if standart version of graycolor or hentai version will be best for general purpose.
@GrayColor thank you very much!!!