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
NoobaiCyberFix 2.0 has the same recipe as NoobaiCyberFix 1.0, but instead of NoobAI Elipson 0.75 I used NoobAI Epsilon 1.0
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
Here's the new recommended negative prompt:
lowres, worst quality, low quality, (bad anatomy, bad hands:1.4), abstract
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
FAQ
Comments (26)
Good job on this one, I find using this model to be more easier than the original Noob. The anatomy issues are still there but not as prevalent as before, the one thing that I like about this is that it is capable of capturing the styles much better in my own testing. Although there are still things that I want to test, overall, it feels better for me to use. And again, nice job on this fix really helps!
Could you upload the temporary model that you create so that I can know how to merge the model
You can make the the temporary model yourself. Here is he workflow
can u share the merge workflow please please please
Hi, which node did you use for "+" and "-" operation? I'm kind of confused since for "+" there's ModelMergeSimple and ModelMergeAdd. Also how much weight you used?
Here is the workflow
https://civitai.com/models/991574?modelVersionId=1110897
I don't know why, but it seems that pony lora works well enough, and if you can't create a good lora in IL, you may be a candidate to use pony lora all the time.
Will you make V-pred 0.5 version?
Maybe when the release version comes out. I think the current version of V-pred has problems with saturation. You can make the merge yourself if you want to check the current v-pred models. Here is the workflow
https://civitai.com/models/991574?modelVersionId=1110897
Please, change from illustrious to SDXL. I can't add in recommended resources your model in my loras :c
bro wth? it is based off ilust model what are you on about?
@makotoyuki It doesn't matter. Firstly it is too deep finetune (12 million arts) and you can't use loras from noobai on illustrious without losses. Secondly on model page it is marked as SDXL 1.0. If your lora model is illustrious you can't add in recommended models NoobAI-XL since it SDXL 1.0. I want to add in recommended Cyberfix but I can't because it is marked as Illistrious.
Very good and very underrated model imo. Thanks for putting this together.
Thanks for your work! Will it be updated again with non v-pred version?
Are there any new non v-pred models? I think the 1.0 epsilon is the latest non v-pred version. If new epsilon models come out, I will probably update CyberFix. I also plan to update CyberFix when final version of the v-pred model is released
@MindInTheDigits I'll be waiting for it :)
Well, after hundred tests I can say that this CyberFix is better than 0.65s NoobAI base.
Someone posted some cyberfixes for 0.65-0.65S vpred
https://huggingface.co/Panchovix/noobai-XL-Vpred-0.65-cyberfix
https://huggingface.co/Panchovix/noobai-XL-Vpred-0.65s-cyberfix
If it helps
Cool! I'm glad to see people using this merge recipe. I've also uploaded the ComfyUI workflow to make it easier to create CyberFix merges
https://civitai.com/models/991574?modelVersionId=1110897
Please make cyberfix for new Epsilon version. They released 1.1.
NoobaiCyberFix 3.0 is ready! Have fun!
@MindInTheDigits thx!
Please make cyberfix for new Epsilon version. They released 1.1.
1.1 colorfull then 1.0
NoobaiCyberFix 3.0 is ready! Have fun!
@MindInTheDigits yeeeeep!!!
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.





