Hugging Face's logo

Laxhar
/
noobai-XL-Vpred-0.5

Text-to-Image
Diffusers
Safetensors
English
stable-diffusion
stable-diffusion-xl
art
Not-For-All-Audiences
Model card Files Community
7
noobai-XL-Vpred-0.5 / README.md
NebulaeWis's picture
NebulaeWis
Update README.md
0242861 verified
preview code
|
raw
history blame
10.7 kB
---
license: other
license_name: fair-ai-public-license-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
language:
- en
base_model:
- Laxhar/noobai-XL_v1.0
pipeline_tag: text-to-image
tags:
- safetensors
- diffusers
- stable-diffusion
- stable-diffusion-xl
- art
library_name: diffusers
---
<h1 align="center"><strong style="font-size: 48px;">NoobAI XL V-Pred 0.5</strong></h1>
# 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](https://huggingface.co/Laxhar)
- **Model Type**: Diffusion-based text-to-image generative model
- **Fine-tuned from**: Laxhar/noobai-XL_v1.0
- **Sponsored by from**: [Lanyun Cloud](https://cloud.lanyun.net)
---
# How to Use the Model.
## Method I: [reForge](https://github.com/Panchovix/stable-diffusion-webui-reForge/tree/dev_upstream)
1. Install reForge by following the instructions in the repository;
2. Switch to `dev_upstream_experimental` branch by running `git checkout dev_upstream_experimental`;
3. Launch reForge WebUI;
4. Find "_Advanced Model Sampling for Forge_" accordion at the bottom of the "_txt2img_" tab;
5. Enable "_Enable Advanced Model Sampling_";
6. Select "_v_prediction_" in the "_Discrete Sampling Type_" checkbox group.
7. Generate images!
## Method II: [ComfyUI](https://github.com/comfyanonymous/ComfyUI)
SAMLPLE with NODES
[comfy_ui_workflow_sample](/Laxhar/noobai-XL-Vpred-0.5/blob/main/comfy_ui_sample.png)
## Method III: [WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
Note that dev branch is not stable and **may contain bugs**.
1. (If you haven't installed WebUI) Clone the repository:
```bash
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
```
2. Switch to `dev` branch:
```bash
git switch dev
```
3. Pull latest updates:
```bash
git pull
```
## Method IV: [Diffusers](https://huggingface.co/docs/diffusers/en/index)
```python
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")
```
4. Launch WebUI and use the model as usual.
**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 Range | Quality Tags |
| :--------------- | :------------- |
| > 95th | masterpiece |
| > 85th, <= 95th | best quality |
| > 60th, <= 85th | good quality |
| > 30th, <= 60th | normal quality |
| <= 30th | worst quality |
## Aesthetic Tags
| Tag | Description |
| :-------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| very awa | Top 5% of images in terms of aesthetic score by [waifu-scorer](https://huggingface.co/Eugeoter/waifu-scorer-v4-beta) |
| worst aesthetic | All the bottom 5% of images in terms of aesthetic score by [waifu-scorer](https://huggingface.co/Eugeoter/waifu-scorer-v4-beta) and [aesthetic-shadow-v2](https://huggingface.co/shadowlilac/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 Range | Period tag |
| :--------- | :--------- |
| 2005-2010 | old |
| 2011-2014 | early |
| 2014-2017 | mid |
| 2018-2020 | recent |
| 2021-2024 | newest |
## Dataset
- The latest Danbooru images up to the training date (approximately before 2024-10-23)
- E621 images [e621-2024-webp-4Mpixel](https://huggingface.co/datasets/NebulaeWis/e621-2024-webp-4Mpixel) dataset on Hugging Face
**Communication**
- **QQ Groups:**
- 875042008
- 914818692
- 635772191
- **Discord:** [Laxhar Dream Lab SDXL NOOB](https://discord.com/invite/DKnFjKEEvH)
# 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
For the open source community, you need to:
- 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](https://civitai.com/user/L_A_X) | [Liblib.art](https://www.liblib.art/userpage/9e1b16538b9657f2a737e9c2c6ebfa69) | [Huggingface](https://huggingface.co/LAXMAYDAY)
- **li_li:** [Civitai](https://civitai.com/user/li_li) | [Huggingface](https://huggingface.co/heziiiii)
- **nebulae:** [Civitai](https://civitai.com/user/kitarz) | [Huggingface](https://huggingface.co/NebulaeWis)
- **Chenkin:** [Civitai](https://civitai.com/user/Chenkin) | [Huggingface](https://huggingface.co/windsingai)
- **Euge:** [Civitai](https://civitai.com/user/Euge_) | [Huggingface](https://huggingface.co/Eugeoter) | [Github](https://github.com/Eugeoter)
## Contributors
- **Narugo1992**: Thanks to [narugo1992](https://github.com/narugo1992) and the [deepghs](https://huggingface.co/deepghs) team for open-sourcing various training sets, image processing tools, and models.
- **Mikubill**: Thanks to [Mikubill](https://github.com/Mikubill) for the [Naifu](https://github.com/Mikubill/naifu) trainer.
- **Onommai**: Thanks to [OnommAI](https://onomaai.com/) for open-sourcing a powerful base model.
- **V-Prediction**: Thanks to the following individuals for their detailed instructions and experiments.
- adsfssdf
- [bluvoll](https://civitai.com/user/bluvoll)
- [bvhari](https://github.com/bvhari)
- [catboxanon](https://github.com/catboxanon)
- [parsee-mizuhashi](https://huggingface.co/parsee-mizuhashi)
- [very-aesthetic](https://github.com/very-aesthetic)
- **Community**: [aria1th261](https://civitai.com/user/aria1th261), [neggles](https://github.com/neggles/neurosis), [sdtana](https://huggingface.co/sdtana), [chewing](https://huggingface.co/chewing), [irldoggo](https://github.com/irldoggo), [reoe](https://huggingface.co/reoe), [kblueleaf](https://civitai.com/user/kblueleaf), [Yidhar](https://github.com/Yidhar), ageless, 白玲可, Creeper, KaerMorh, 吟游诗人, SeASnAkE, [zwh20081](https://civitai.com/user/zwh20081), Wenaka⁧~喵, 稀里哗啦, 幸运二副, 昨日の約, 445, [EBIX](https://civitai.com/user/EBIX), [Sopp](https://huggingface.co/goyishsoyish), [Y_X](https://civitai.com/user/Y_X), [Minthybasis](https://civitai.com/user/Minthybasis), [Rakosz](https://civitai.com/user/Rakosz)