底模：SDXL

主页：https://civitai.com/models/833294/noobai-xl-nai-xl

版本：Epsilon-pred 0.75-Version

artist:konya_karasue,artist:hoji(hooooooooji1029),michiking,artist:ningen_mame,artist:kedama_milk,[[mignon]],[artist:kani_biimu],artist:ogipote,artist:sy4,noyu_(noyu23386566),1girl, solo, bow, long hair, thighhighs, hair bow, pink hair, flower, rose, weapon, holding, petals, dress, bangs, very long hair, gloves, white thighhighs, long sleeves, looking at viewer, hair ornament, holding weapon, white dress, closed mouth, pink bow, garter straps, sword, smile, pink eyes, white gloves, knife, hair between eyes, red rose, butterfly hair ornament, red flower, feet out of frame, holding sword, white bow, holding knife

water pipe,Black border,incomplete,Cinematic Perspective,Cinematic,Focus,Solo Focus,borders,incomplete backgrounds,pollution,border,white border,red border,Close hand,one handed,Multi handed,hand holding,tongs,Black border,black frame,solo,focus,dark skinned,Hand in hand,handshake,dark skin,halo,glasses,watermark,doll,word,words,bad feet,lace,simple background,white background,black background,lowres,{bad},error,fewer,extra,missing,worst quality,jpeg artifacts,bad quality,watermark,unfinished,displeasing,chromatic aberration,tomboy,pourgirl,solo,signature,extra digits,artistic error,username,scan,[abstract],bad anatomy,bad hands,mismatched pupils,heart-shaped pupils,glowing eyes,censored,anatomy,text,missing fingers,fewer digits,cropped,low-resolution,normal quality,signature,blurry,androgyny,otokonoko,male daughter,male girl,futanari,futanarikko,androgyny,

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

New Version is training on 32*H100

https://huggingface.co/Laxhar/sdxl_noob

Follow-up models and technical reports will be posted on huggingface

Communication qq groups：①875042008 ②914818692 ③635772191

DISCORD: Laxhar Dream Lab SDXL NOOB

We extend our sincere gratitude to our esteemed GPU sponsors for their generous support: https://cloud.lanyun.net

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!!!

Current Status

This is an 50% 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.

NoobAI-XL Short Test Report V0.1

https://nx9nemngdhk.feishu.cn/docx/XcAddUhDOo57U7x7MbXcE6VNnYc

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.