Sign In

NoobaiCyberFix

401
3.6k
99
Updated: Dec 24, 2024
base modelanime
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
1,131
Reviews
Published
Dec 2, 2024
Base Model
Illustrious
Hash
AutoV2
A980F27B57

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), abstract

NoobaiCyberFix 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), abstract

Anatomy, 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, signature

Recipe 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://civitai.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!

NoobAI-Epsilon075

Illustrious-XL

cyberrealisticXL_v31

stable-diffusion-xl-base-1.0