NoobaiCyberFix 3.0
Recipe
NoobaiCyberFix 3.0 has the same recipe as NoobaiCyberFix 1.0, but instead of NoobAI Elipson 0.75 I used NoobAI Elipson 1.1
Recommended CFG: 7-10
New recommended negative prompt
lowres, (worst quality, low quality:1.2), (bad anatomy, bad hands:1.4), abstractNoobaiCyberFix 2.0
Recipe
NoobaiCyberFix 2.0 has the same recipe as NoobaiCyberFix 1.0, but instead of NoobAI Elipson 0.75 I used NoobAI Epsilon 1.0
Brightness
NoobAI Epsilon 1.0 seems to respond much more strongly to prompts, and because of this, it is recommended to reduce the CFG if you get too bright images. It is also recommended to reduce the power of the “low quality, worst quality” tags
New recommended negative prompt
lowres, worst quality, low quality, (bad anatomy, bad hands:1.4), abstractAnatomy, characters and styles
I also noticed that NoobAI Epsilon 1.0 has a bit more anatomy issues, and because of that NoobaiCyberFix 2.0 also has a bit more anatomy issues compared to NoobaiCyberFix 1.0, and because of that I still prefer NoobaiCyberFix 1.0 in some cases. But at the same time, NoobAI Epsilon 1.0 knows characters and styles better than NoobAI Epsilon 0.75, so NoobaiCyberFix 2.0 knows characters and styles better too. I think it is good idea to try both NoobaiCyberFix 2.0 and NoobaiCyberFix 1.0 and decide which you like better
NoobaiCyberFix 1.0
Purpose of this merge
The purpose of this model is to fix the anatomy problems of model NoobAI-Epsilon075, while keeping 100% of its knowledge and style. NoobAI-Epsilon075 is a great model, it knows almost all characters and styles from Danbooru, but it has some anatomy issues and this merge completely solves this problem. If you use NoobAI-Epsilon075 for SFW purposes, you will hardly notice any difference between this merge and the original model, because the goal was to keep all the knowledge of NoobAI-Epsilon075, and visually this model is almost indistinguishable from NoobAI-Epsilon075. But if you are a man of culture and like Pony models, you will definitely like this one, because this merge gives the model a very good knowledge of anatomy, almost at Pony level
Recommended negative prompt
lowres, (worst quality, low quality, bad anatomy, bad hands:1.3), abstract, signatureRecipe of the merge
1 Create temporary model
TempModel = NoobAI-Epsilon075 + cyberrealisticXL_v31 - stable-diffusion-xl-base-1.0
2 Remove CLIP from TempModel and replace it by CLIP from NoobAI-Epsilon075
I did this step in ComfyUI.
Here is the workflow
https://civarchive.com/models/991574?modelVersionId=1110897
Logic behind this merge
cyberrealisticXL_v31 is a general purpose model without any specific style, just like stable-diffusion-xl-base-1.0, and so if you replace the stable-diffusion-xl-base-1.0 weights with cyberrealisticXL_v31 weights in any model, it shouldn't change the model's style and its knowledge much. But at the same time, cyberrealisticXL_v31 has much better anatomy knowledge than sd-xl-1.0, and because of this, it should greatly improve the anatomy knowledge of any model, and in the case of NoobaiCyberFix, it worked exactly as I expected. In theory, you can use this recipe to improve the anatomy knowledge of any model that needs it
Big thanks to the creators of these models!
Description
FAQ
Comments (16)
why didnt you merge noobai-v1 instead since its out?
I noticed that noobai-v1 came out already after I uploaded the merge. Probably I will make a new version of this merge, already with noobai-v1
I uploaded a new version
Holy shit, I love you so much. I've been doing fucks number of trial and error to make real good hands and feet with the original model for hours and hours of t2t and inpainting. This pretty much solves it with just a mere few generations. Not even inpainting is needed. THANK YOU!
This recipe is unbelivable. You're a genious
I can't express my gratitude enough, thank you so much for this chkpnt! Looking forward for v1.0 merge
Its magic. How about leaving merge recipe 1 as NoobAI v0.75 and replacing recipe 2's CLIP with NoobAI v1.0?
You can try version 2.0, it is based on Noobai Epsilon 1.0
I think 1.0 is better for CLIP, and 0.5 or 0.75 is better for UNET. I tried making it myself, and it looks good, so please try it if you feel like it.
@meeeetia can u share 🙏🏻
@meeeetia curious about the result.The picture quality of 0.75 is very good, and the style of 1.0 is more complete. I am really looking forward to combining the two.
@meeeetia would be grateful if u could share your merged model 🙏
@dr_dark_flames @393476960378 @Telescopa posted it a few days ago, so go to my profile and take a look.
@meeeetia ok, thank u
@meeeetia 非常感谢,虽然不知道里面发生了什么但是他做出了我想要的画风!
nice!
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.




