Model Introduction

This image generation model, based on Laxhar/noobai-XL_v1.0, leverages full Danbooru and e621 datasets with native tags and natural language captioning.

Implemented as a v-prediction model (distinct from eps-prediction), it requires specific parameter configurations - detailed in following sections.

Special thanks to my teammate euge for the coding work, and we're grateful for the technical support from many helpful community members.

⚠️ IMPORTANT NOTICE ⚠️

THIS MODEL WORKS DIFFERENT FROM EPS MODELS!

PLEASE READ THE GUIDE CAREFULLY!

Model Details

• Developed by: Laxhar Lab

• Model Type: Diffusion-based text-to-image generative model

• Fine-tuned from: Laxhar/noobai-XL_v1.0

• Sponsored by from:

  Lanyun Cloud

  Civitai & Seaart

• Collaborative testing:

  LiblibAI

  Nieta

---

How to Use the Model.

Guidebook for NoobAI XL:

ENG:

https://civitai.com/articles/8962

CHS:

https://fcnk27d6mpa5.feishu.cn/wiki/S8Z4wy7fSiePNRksiBXcyrUenOh

Method I: reForge

1. (If you haven't installed reForge) Install reForge by following the instructions in the repository;

2. Launch WebUI and use the model as usual!

Method II: ComfyUI

SAMLPLE with NODES

comfy_ui_workflow_sample

Method III: WebUI

Note that dev branch is not stable and may contain bugs.

1. (If you haven't installed WebUI) Install WebUI by following the instructions in the repository. For simp

2.Switch to dev branch:

git switch dev

3. Pull latest updates:

git pull

4. Launch WebUI and use the model as usual!

Method IV: Diffusers

import torch

from diffusers import StableDiffusionXLPipeline

from diffusers import EulerDiscreteScheduler



ckpt_path = "/path/to/model.safetensors"

pipe = StableDiffusionXLPipeline.from_single_file(

    ckpt_path,

    use_safetensors=True,

    torch_dtype=torch.float16,

)

scheduler_args = {"prediction_type": "v_prediction", "rescale_betas_zero_snr": True}

pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, **scheduler_args)

pipe.enable_xformers_memory_efficient_attention()

pipe = pipe.to("cuda")



prompt = """masterpiece, best quality,artist:john_kafka,artist:nixeu,artist:quasarcake, chromatic aberration, film grain, horror \(theme\), limited palette, x-shaped pupils, high contrast, color contrast, cold colors, arlecchino \(genshin impact\), black theme,  gritty, graphite \(medium\)"""

negative_prompt = "nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro"



image = pipe(

    prompt=prompt,

    negative_prompt=negative_prompt,

    width=832,

    height=1216,

    num_inference_steps=28,

    guidance_scale=5,

    generator=torch.Generator().manual_seed(42),

).images[0]



image.save("output.png")

Note: Please make sure Git is installed and environment is properly configured on your machine.

---

Recommended Settings

Parameters

• CFG: 4 ~ 5

• Steps: 28 ~ 35

• Sampling Method: Euler (⚠️ Other samplers will not work properly)

• Resolution: Total area around 1024x1024. Best to choose from: 768x1344, 832x1216, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768

Prompts

• Prompt Prefix:

masterpiece, best quality, newest, absurdres, highres, safe,

• Negative Prompt:

nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro

Usage Guidelines

Caption

<1girl/1boy/1other/...>, <character>, <series>, <artists>, <special tags>, <general tags>, <other 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 RangeQuality Tags> 95thmasterpiece> 85th, <= 95thbest quality> 60th, <= 85thgood quality> 30th, <= 60thnormal quality<= 30thworst quality

Aesthetic Tags

TagDescriptionvery awaTop 5% of images in terms of aesthetic score by waifu-scorerworst aestheticAll the bottom 5% of images in terms of aesthetic score by waifu-scorer and aesthetic-shadow-v2......

Date Tags

There are two types of date tags: year tags and period tags. For year tags, use year xxxx format, i.e., year 2021. For period tags, please refer to the following table:

Year RangePeriod tag2005-2010old2011-2014early2014-2017mid2018-2020recent2021-2024newest

Dataset

• The latest Danbooru images up to the training date (approximately before 2024-10-23)

• E621 images e621-2024-webp-4Mpixel dataset on Hugging Face

Communication

• QQ Groups:

  • 875042008

  • 914818692

  • 635772191

  • 870086562

• Discord: Laxhar Dream Lab SDXL NOOB

How to train a LoRA on v-pred SDXL model

A tutorial is intended for LoRA trainers based on sd-scripts.

article link: https://civitai.com/articles/8723

Utility Tool

Laxhar Lab is training a dedicated ControlNet model for NoobXL, and the models are being released progressively. So far, the normal, depth, and canny have been released.

Model link: https://civitai.com/models/929685

Model License

This model's license inherits from https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0 fair-ai-public-license-1.0-sd and adds the following terms. Any use of this model and its variants is bound by this license.

I. Usage Restrictions

• Prohibited use for harmful, malicious, or illegal activities, including but not limited to harassment, threats, and spreading misinformation.

• Prohibited generation of unethical or offensive content.

• Prohibited violation of laws and regulations in the user's jurisdiction.

II. Commercial Prohibition

We prohibit any form of commercialization, including but not limited to monetization or commercial use of the model, derivative models, or model-generated products.

III. Open Source Community

To foster a thriving open-source community,users MUST comply with the following requirements:

• Open source derivative models, merged models, LoRAs, and products based on the above models.

• Share work details such as synthesis formulas, prompts, and workflows.

• Follow the fair-ai-public-license to ensure derivative works remain open source.

IV. Disclaimer

Generated models may produce unexpected or harmful outputs. Users must assume all risks and potential consequences of usage.

Participants and Contributors

Participants

• L_A_X: Civitai | Liblib.art | Huggingface

• li_li: Civitai | Huggingface

• nebulae: Civitai | Huggingface

• Chenkin: Civitai | Huggingface

• Euge: Civitai | Huggingface | Github

Contributors

• Narugo1992: Thanks to narugo1992 and the deepghs team for open-sourcing various training sets, image processing tools, and models.

• Mikubill: Thanks to Mikubill for the Naifu trainer.

• Onommai: Thanks to OnommAI for open-sourcing a powerful base model.

• V-Prediction: Thanks to the following individuals for their detailed instructions and experiments.

  • adsfssdf

  • bluvoll

  • bvhari

  • catboxanon

  • parsee-mizuhashi

  • very-aesthetic

  • momoura

  • madmanfourohfour

• Community: aria1th261, neggles, sdtana, chewing, irldoggo, reoe, kblueleaf, 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, EBIX, Sopp, Y_X, Minthybasis, Rakosz, 孤辰NULL, 汤人烂, 沅月弯刀,David，

描述:

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.

训练词语: