NoobAI-XL (NAI-XL)
Epsilon-pred 1.0-Version
L_A_X
this is an image generation model based on training from Illustrious-xl, and continued trained by Laxhar Lab.
https://civitai.com/models/795765/illustrious-xl
It utilizes the latest full Danbooru and e621 datasets for training, with native tags caption.
The version uploaded on 8 October trained 5 epochs on 8*H100, as a Early Access Version.
And huggingface page of Lab
https://huggingface.co/Laxhar/sdxl_noob
Follow-up models and technical reports will be posted on huggingface
This version of the model improves the fit of the characters and styles in Illustrious-xl 0.1ver, and the specific characteristics of the characters have a better representation. Laxhar lab is currently continuing to train the new version of the open-source model of XL on the basis of this beta version in the hope of minimising the use of lora, and releasing a more Noob-friendly, one-click SDXL anime model!
Note: The model name and other details are subject to change.
This model is still undergoing training!!!
This model is still undergoing training!!!
This model is still undergoing training!!!
Important Information
-We are compelled to release an extremely premature version of this model against our wishes.
-The model is still actively in training and far from completion.
-This forced open-source version will be released under the same license terms as its base model,Illustrious-XL-v0.1.
Current Status
This is an early test version intended for internal use. However, we are considering allowing limited external testing.
Datasets
- Danbooru (Pid: 1~7,600,039):
https://huggingface.co/datasets/KBlueLeaf/danbooru2023-webp-4Mpixel
- Danbooru (Pid > 7,600,039):
https://huggingface.co/datasets/deepghs/danbooru_newest-webp-4Mpixel
- E621 Data as of 2024-04-07 :
https://huggingface.co/datasets/NebulaeWis/e621-2024-webp-4Mpixel
Caption
<1girl/1boy/1other/...>, <character>, <series>, <artists>, <special tags>, <general tags>
Quality Tags
For quality tags, we evaluated image popularity through the following process:
Data normalization based on various sources and ratings.
Application of time-based decay coefficients according to date recency.
Ranking of images within the entire dataset based on this processing.
Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years.
Percentile Range Quality Tags
> 95th masterpiece
> 85th, <= 95th best quality
> 60th, <= 85th good quality
> 30th, <= 60th normal quality
<= 30th worst quality
In the CCIP test, noobaiXL showed an improvement of approximately 2% compared to its base model. Based on data from over 3,500 characters, 89.2% of the characters achieved a CCIP score higher than 0.9. Given the current model performance, it is necessary to further expand the dataset for the existing CCIP test
Monetization Prohibition:
● You are prohibited from monetizing any close-sourced fine-tuned / merged model, which disallows the public from accessing the model's source code / weights and its usages.
● As per the license, you must openly publish any derivative models and variants. This model is intended for open-source use, and all derivatives must follow the same principles.
License
This model is released under Fair-AI-Public-License-1.0-SD
Plz check this website for more information:
Freedom of Development (freedevproject.org)
Many thanks to those who have gone before us for their experience and training, and I welcome other labs to pick up the slack and train the community anime model better and better!
The participants, contributors, and testers of the model are acknowledged below
（listed in no particular order）
participants
L_A_X https://civitai.com/user/L_A_X
https://www.liblib.art/userpage/9e1b16538b9657f2a737e9c2c6ebfa69
li_li https://civitai.com/user/li_li
nebulae https://civitai.com/user/kitarz
Chenkin https://civitai.com/user/Chenkin
contributors
Narugo1992:
Thanks to narugo1992 and the deepghs he leads for open-sourcing a range of training sets, image processing tools and models.
https://huggingface.co/deepghs
Naifu：
Training scripts
https://github.com/Mikubill/naifu
Onommai：
Thanks to onommai open source for such a powerful base model.
aria1th261 https://civitai.com/user/aria1th261
kblueleaf https://civitai.com/user/kblueleaf
Euge https://civitai.com/user/Euge_
Yidhar https://github.com/Yidhar
ageless 白玲可 Creeper KaerMorh 吟游诗人 SeASnAkE zwh20081 Wenaka~喵 稀里哗啦 幸运二副
昨日の約. 445
What is NoobAI-XL (NAI-XL)?
NoobAI-XL (NAI-XL) is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user L_A_X. Derived from the powerful Stable Diffusion (SDXL 1.0) model, NoobAI-XL (NAI-XL) has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that NoobAI-XL (NAI-XL) is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, base model, based.
With a rating of 0 and over 0 ratings, NoobAI-XL (NAI-XL) is a popular choice among users for generating high-quality images from text prompts.
Can I download NoobAI-XL (NAI-XL)?
Yes! You can download the latest version of NoobAI-XL (NAI-XL) from here.
How to use NoobAI-XL (NAI-XL)?
To use NoobAI-XL (NAI-XL), download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like NoobAI-XL (NAI-XL), check out our crash course in AI image generation.
Popularity
Info
Version Epsilon-pred 1.0-Version: 1 File
About this version: Epsilon-pred 1.0-Version
Introduction to NoobAI-XL EPS 1.0 Vwe by Laxhar Dream Lab
尊敬的各位AIGC爱好者，
Dear All,
很高兴向大家介绍Laxhar Dream Lab推出的:NoobAI-XL EPS 1.0
该模型使用了1270万张图像（最新的Danbooru和e621完整数据集），在32*H100 GPUs上进行了32个epoch的训练（共计38.4亿步），已支持D站solo count 80图的角色和风格。
We are honored to introduce to you the NoobAI-XL EPS 1.0 model launched by Laxhar Dream Lab. This model has been trained on 12.7 million images, including the latest complete datasets from Danbooru and e621, and was trained for 32 epochs on 32 H100 GPUs (a total of 3.84 billion steps), now supporting D station solo count 80 characters and artistic styles.
特别鸣谢
Special Acknowledgments
本版本训练过程中，来自nieta的算法实习生@li_li对trainer发挥了重要作用，在此进行特别鸣谢，感谢li_li作为Laxhar Lab成员的辛勤付出。
Lanyun作为本项目的算力赞助商，其对于开源社区的巨大贡献我们无以言表，Liblib AI在训练过程中提供了测试设备，也一同在此致谢。
同时，解构原典社群的伙伴们也在训练过程中进行了详细的测试与辅助工作，限于人数众多，无法一一鸣谢，在此对各位一并致以最诚挚的感谢!
In the training process of this version, algorithm intern @li_li from nieta played a significant role in the training, for which we express our special thanks here. We appreciate the hard work of li_li as a member of Laxhar Lab.
Lanyun, as the computational sponsor of this project, has made an invaluable contribution to the open-source community, for which we are immensely grateful. Liblib AI also provided testing equipment during the training process, and we extend our thanks to them as well.
At the same time, our partners at DCTN have also carried out detailed testing and auxiliary work during the training process. Due to the large number of people involved, it is not possible to thank each one individually, so we extend our sincerest gratitude to all!
To do List
Laxhar Dream Lab目前正全力致力于进一步完善SDXL开源生态，后续我们的工作是开发v预测版与noob配套的专用controlNet，以及更多配套插件，提高模型的泛用度，这也是这个模型明明的初衷，即“菜鸟也能用的很好的模型。”
Laxhar Dream Lab is currently fully committed to further improving the SDXL open-source ecosystem. Our next steps include developing a v-prediction version and a dedicated controlNet for NoobAI-XL, as well as additional complementary plugins, to enhance the versatility of the model. This is also the original intention of this model - "A model that even noobs can use well."
我们衷心感谢所有参与过测试和训练的人员，感谢大家的支持，希望开源社区变得越来越好！
We sincerely thank all those who have participated in testing and training, and we appreciate everyone's support. We hope that the open-source community will continue to grow and improve.
12 Versions
Go ahead and upload yours!
