Diffus
ホーム
アフィリエイト
料金
SD3
API
モデル
ギャラリー
始める
モデル/NoobAI-XL (NAI-XL) - V-Pred-1.0-Version

NoobAI-XL (NAI-XL) - V-Pred-1.0-Version

L_A_X
|
7/16/2025
|
11:48:36 AM
| Discussion
Realistic portrait of a young woman with brown hair in a loose bun, wearing thick framed glasses and a brown jacket over a black turtleneck, holding a phone to her ear, sitting outdoors in a park under a blue morning sky with scattered clouds.
Realistic portrait of a girl with brown hair and green eyes wearing a white turtleneck sweater, green overalls, and a green hair ribbon, looking at the viewer in an outdoor field.
A dynamic illustration of a knight wearing full white armor and a winged helmet, wielding a polearm and round shield with a red cape flowing behind.
Side profile of a woman wearing a detailed orange and black space combat suit standing in front of an alien world backdrop, painted digitally with realistic shading.
Profile portrait of a female geisha with white hair styled in twin braids and adorned with a kanzashi hair ornament, wearing a red kimono indoors under dim lighting.
Portrait of a blonde woman with long hair and parted lips, wearing a choker, bathed in orange and teal colors with digital glitch obscuring her eyes against a white background.
Photorealistic depiction of a seductive woman with wolf cut hairstyle, black leather armor adorned with glowing red runes, immersed in swirling liquid metal magic with vivid red accents against a black background.
Close-up of a girl with coral eyes and multicolored short hair wearing a detailed ornamental headdress with orange and blue flowers, making a heart shape with her hands against a red background.
Two young adults with dark hair floating peacefully in a calm turquoise ocean under a blue sky with distant mountains.
A dark armored knight clutching a glowing red sword with a cracked and weathered white armor, set against a soft, abstract light background.
A Valkyrie clad in Nordic armor with huge wings soars in golden celestial light, riding a dark horse atop a rocky cliff, holding a spear.
Monochrome profile portrait of a dark-skinned male with black hair in a high ponytail, red eyes, black kimono, and a smug expression on a red background.

推奨プロンプト

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

year 2024, long hair, best quality, masterpiece, absurdres, newest, highres

推奨ネガティブプロンプト

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

推奨パラメータ

samplers

Euler, Euler a, dpmpp_3m_sde

steps

10 - 40

cfg

4 - 6.5

resolution

768x1344, 832x1216, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768, 808x1152, 1024x1536, 832x1216

other models

noob_v_newtest_b (1a7e3d935d)

推奨ハイレゾパラメータ

upscaler

R-ESRGAN 4x+ Anime6B, 4x-AnimeSharp, 4x-UltraSharp, [Anime]4xUltrasharp

upscale

1.2 - 1.8

steps

15 - 20

denoising strength

0.3 - 0.55

ヒント

Use the Euler sampler only, as other samplers will not work properly.

Use a resolution around 1024x1024, with 832x1216 being the best choice.

Recommended CFG values are between 4 and 5, with steps from 28 to 35.

Refer to the provided guidebooks and community tutorials for detailed usage instructions.

Utilize recommended LoRas listed in the provided resources for enhanced results.

バージョンのハイライト

Merry Christmas! NOOBAI XL-VPred 1.0 has been released! The V prediction series has come to a successful end, and what an interesting journey it has been. Who knows, we might have the chance to do this again in the future. With this, our Laxhar Lab's weekly update plan comes to a grand finale!

By the way, here are the advantages of this version:

1. Fine-tuned with high-quality datasets: We have optimized the model for anatomical accuracy and compositional rationality through meticulous adjustments with high-quality datasets.

2. Flexible style combination weights: The model now offers more flexibility in combining different painting styles, with improved robustness when overlaying multiple styles.

3. Enhanced utility of quality words: The effectiveness of quality words has become more pronounced in this version.

4. A blend of features from the standard and S versions: The color style is vibrant yet less prone to overexposure, combining the best of both worlds.

Usage recommendations and future work:

1. Use with dynamic CFG plugin: We recommend using the dynamic CFG & CFG Rescale plugin when employing the V prediction model to prevent oversaturation or overly gray images. You can refer to the configuration of 0.2 for the best results.

2. Choice of sampling methods: Although NOOBAI XL-VPred 1.0 supports most sampling methods, V prediction does not support the Karras series of sampling. Therefore, we suggest using Euler and DDIM sampling methods for more stable outcomes.

3. Ongoing updates and support: We will continue to update VPred 1.0, including the ControlNet model and other plugins. The main model will also be updated irregularly when there are significant improvements (let's see how the DIT effect of NAI4 is and learn from it), so stay tuned!

Lastly, I must share a personal recommendation: the recent game "MiSide" is truly a great game. It has been a long time since a solo game has moved me so much. I strongly recommend it. Wishing you all a Merry Christmas. After a year of hard work, it's time to rest. Until we meet again in this world of possibilitiesミ(・・)ミ

クリエイタースポンサー

Sponsored by: Lanyun Cloud, Civitai & Seaart

Collaborative testing provided by LiblibAI and Nieta

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

How to Use the Model.

Guidebook for NoobAI XL:

ENG:

https://civitai.com/articles/8962

CHS:

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

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

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

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

Contributors

投稿者

L_A_X avatar

L_A_X

前の画像
Wacky Chaotic Image Upgrader - v1.0 Flux
次の画像
NoiseOffset_By_Stable_Yogi - v1.0
このモデルを使用

モデル詳細

モデルタイプ

Checkpoint

ベースモデル

NoobAI

モデルバージョン

V-Pred-1.0-Version

モデルハッシュ

ea349eeae8

作成者

L_A_X's avatar
L_A_X

ディスカッション

コメントを残すには log in してください。

「NoobAI-XL (NAI-XL) - V-Pred-1.0-Version」による画像

Realistic portrait of a young woman with brown hair in a loose bun, wearing thick framed glasses and a brown jacket over a black turtleneck, holding a phone to her ear, sitting outdoors in a park under a blue morning sky with scattered clouds.
Portrait of a blonde woman with long hair and parted lips, wearing a choker, bathed in orange and teal colors with digital glitch obscuring her eyes against a white background.
A Valkyrie clad in Nordic armor with huge wings soars in golden celestial light, riding a dark horse atop a rocky cliff, holding a spear.
Realistic portrait of a girl with brown hair and green eyes wearing a white turtleneck sweater, green overalls, and a green hair ribbon, looking at the viewer in an outdoor field.
Photorealistic depiction of a seductive woman with wolf cut hairstyle, black leather armor adorned with glowing red runes, immersed in swirling liquid metal magic with vivid red accents against a black background.
Monochrome profile portrait of a dark-skinned male with black hair in a high ponytail, red eyes, black kimono, and a smug expression on a red background.
A dynamic illustration of a knight wearing full white armor and a winged helmet, wielding a polearm and round shield with a red cape flowing behind.
Close-up of a girl with coral eyes and multicolored short hair wearing a detailed ornamental headdress with orange and blue flowers, making a heart shape with her hands against a red background.
Side profile of a woman wearing a detailed orange and black space combat suit standing in front of an alien world backdrop, painted digitally with realistic shading.
Two young adults with dark hair floating peacefully in a calm turquoise ocean under a blue sky with distant mountains.
Profile portrait of a female geisha with white hair styled in twin braids and adorned with a kanzashi hair ornament, wearing a red kimono indoors under dim lighting.
A dark armored knight clutching a glowing red sword with a cracked and weathered white armor, set against a soft, abstract light background.