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
As you all may know, noob version 1.0 has been released. Personally, I feel that while it’s gotten smarter, it has also become somewhat harder to handle. At times, it even seems to have similar issues to those seen in the older ILXL 0.1 version. To address this, I recalled the approach that somewhat resolved these issues in the past and applied slight modifications.
reorganized the merge ratios and order previously in use.
I used a base that combines the TE from noob 1.0 with the unet from 0.75 in a balanced ratio, to retain noob 1.0’s knowledge while keeping a familiar feel.
Additionally, I aimed for a version that has a 3.5-like feel, as I considered that the style difference between my models v3.0 and v4.0 may lead to mixed preferences.
The result is now more natural and consistent
As with version 4.0, noise in standard resolution images has been reduced, but it’s still better to use hires if the image isn’t a close-up.
FAQ
Comments (2)
Do you think the visuals in version 5.0 are a bit too bright? Even at night, it’s still very bright, which makes the characters’ skin look excessively pale, almost like there’s a flashlight constantly shining on them. (I feel like this makes some scenes lose their vibrancy.) Is this your personal preference? Aside from this issue, I think 5.0 is much better than 3.0 overall. The understanding capability has greatly improved, and the eyes are no longer blurry (the eyes in 3.0 were really blurry). If it weren’t for the characters being too bright in my generated images, I would definitely switch from 3.0 to 5.0. Also, thank you so much for the model you’ve created—it allowed me to achieve the art style I love. If you have time, I’d be very happy if you could check out my works here: https://www.pixiv.net/users/31655021. They are all based on your 3.0 version.
It’s true that my models tend to appear brighter compared to others.
Personally, I follow the theory that, aesthetically, people tend to prefer slightly brighter images, even if the content is the same, so I’ve adjusted accordingly.
Additionally, when using tools like hires or Photoshop for post-processing, images that are too dark, overly saturated, or high in contrast are more challenging to edit, leading to these results.
However, I’m aware that some images come out overly bright, almost as if light is spilling over. I’ll try to adjust this more in the next version, whenever that may be.