First of all, thank you to those who always make good models.
Do not share this model on all other sites.
Especially not on fucking [PixAI].
I didn't want to write something like this here, but I have no choice. I create and share models based on other people's work. Not that I haven't put in the effort, but it's not entirely my own creation, so I never intend to profit from this model. I share it here in the hope that any individual user can freely use it.
However, I believe that sharing a model itself is very different from providing an image generation service—especially when the latter is used to make money as the main business.
I don't know how many of you will read this, but please be aware: [PixAI] is stealing models and LoRA from CivitAI without permission. In fact, they even, disgustingly, officially support a feature that steals models.
I confirmed that my models were being used without my permission and requested their deletion, but the process was handled incredibly slowly, taking a full week. I asked them to take care to ensure that such incidents wouldn't happen again, yet after I uploaded this v10 version, it was stolen in just three days.
If any of you are also creating and sharing models or LoRA, please check to see if those petty thieves have stolen your valuable work.
[v12]
It’s been a while—we meet again at version 13. As the clock has come full circle, I took extra time to present something even better.
I merged for slightly more aesthetic outputs while preserving each art style.
Until now, the focus was on consistency of style and strong impact (contrast or saturation). This time, I’ve aimed for softer, more natural results and tried to emphasize detail. There are similarities to previous versions, but many things have changed.
If you find that my model is uploaded on other sites (especially PixAI), please contact me at any time. It wasn’t uploaded by me—it was stolen without my permission.
This description was translated using ai and may not be perfect.
[Intro]
Hi there.
This model was created based on NoobAI, with the UNet from other SDXL models merged and some LoRA training added.
Ultimately, my goal was to maintain the core performance of model while achieving a slight quality improvement. However, as an average person without special techniques or high-end hardware, I aimed for “good” rather than “perfect.” As a result, some outcomes may lean in a particular direction, but I believe they’re still enjoyable.
The improvements I focused on are:
Slightly better hands
More consistent quality
More natural compositions
Balanced, non-overwhelming color tones
Aesthetic adjustments, and more.
Recommended Settings
This model is a v-pred model. It is available in the
A1111 webui dev version
reforge
comfyui
Parameters:
CFG: 4~7
Steps: 25~32
Sampling & Schedule:
Generally, the combination of [Euler a] and [SGM Uniform] is a safe choice.
Personally, the combination of [Euler Negative] and [Align Your Steps] provides more diverse results and effective noise handling, allowing clean results even in standard resolutions.
(Other settings are generally similar to those for NoobAI.)
License
This model adheres to the following [license] and is available for non-commercial use only. Commercial use is prohibited.
Thank you.
Description
I have replaced several of the models used for merging after a long time and readjusted all the merge ratios.
Still, I tried to maintain the original style.
(It somewhat feels like a mix between version 10 and version 9.)
In the previous version, issues occurred where a black background would appear or the contrast would become too strong, even unintentionally (when no prompt was provided).
I fixed this to reduce the frequency of such occurrences. Therefore, if you want strong contrast or a dark background, it is recommended to add a prompt like [black background] at the end of your prompt.
(This may make the contrast seem lower.)
Additionally, I fixed an issue in version 10 where the reproduction of some art styles was lacking compared to version 9.
If you find that my model is uploaded on [Pixai], please contact me at any time.
It wasn’t uploaded by me—it was stolen without my permission.
FAQ
Comments (4)
Thanks for your great work.
I have been using your model and I love its style and lighting, but I found that starting with the 9.0V version, even if I lower the CFG to 3, the resulting pictures are still overexposed and oversaturated. Is there a way to improve this?
First of all, thank you for using my model.
The issue occurs because, in order to solve one of the chronic problems I focus on when creating models—namely, that images don’t come out sufficiently bright or dark—I added extra offset noise. Of course, I understand if you find these changes unsatisfactory.
This phenomenon is a basic characteristic of the model and is influenced by several factors, so while it may be effective, I can’t guarantee it will work for everyone. However, here are a few suggested solutions:
Prompt Adjustment:
If you are using art style prompts, this model is quite sensitive to them. Reducing or removing prompts that produce overly strong contrast or vivid color may help. Also, if an image that should be bright turns out dark (or vice versa), you can try adding “white background” or “black background” at the end of your prompt.
Sampling & Schedule Changes:
Generally, sampling methods in the Euler series might yield more subdued results. However, I can’t guarantee this until you give it a try.
Apply CFG Rescale:
You can use the script from the link below to apply a CFG Rescale in the range of about 0.1 to 0.5, which might improve the outcome. Increasing the value too much could make the image look dull, and as for the color fix, in my opinion, it might currently have a counterproductive effect.
CFG Rescale Script
Finally, although it might be a little inconvenient, you can definitively address this issue by installing the extension at the link below:
Vectorscope Extension
This will allow you to adjust various parameters directly when generating images.
Thank you.
@NaGaRi Thank you for your reply! I have been using Vectorscope and CFG Rescale to try to improve it, but the effect achieved by the former is not natural enough, and the latter will change the color of the image, so I'm still trying to find a better solution.
@0xSeiunSky Got it. If I find a suitable solution in the future, I’ll be sure to let you know :)