|
--- |
|
license: agpl-3.0 |
|
language: |
|
- en |
|
- vi |
|
library_name: diffusers |
|
pipeline_tag: text-to-image |
|
tags: |
|
- art |
|
- pytorch |
|
--- |
|
|
|
# Waifumake (●'◡'●) AI Art model. |
|
|
|
![](logo.png) |
|
|
|
A single student training an AI model that generates art. |
|
|
|
## **New model avalable** : [waifumake-full-v2](waifumake-full-v2.safetensors)! |
|
## What's new in v2: |
|
- Fix color loss. |
|
- Increase image quality. |
|
|
|
## Introduction: |
|
- It's an AI art model for converting text to images, images to images, inpainting, and outpainting using Stable Diffusion. |
|
- The AI art model is developed with a focus on the ability to draw anime characters relatively well through fine-tuning using Dreambooth. |
|
- It can be used as a tool for upscaling or rendering anime-style images from 3D modeling software (Blender). |
|
- Create an image from a sketch you created from a pure drawing program. (MS Paint) |
|
- The model is aimed at everyone and has limitless usage potential. |
|
|
|
## Used: |
|
- For 🧨 Diffusers Library: |
|
```python |
|
from diffusers import DiffusionPipeline |
|
|
|
pipe = DiffusionPipeline.from_pretrained("Ojimi/waifumake-full") |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "1girl, animal ears, long hair, solo, cat ears, choker, bare shoulders, red eyes, fang, looking at viewer, animal ear fluff, upper body, black hair, blush, closed mouth, off shoulder, bangs, bow, collarbone" |
|
image = pipe(prompt, negative_prompt="lowres, bad anatomy").images[0] |
|
``` |
|
|
|
- For Web UI by Automatic1111: |
|
```bash |
|
#Install Web UI. |
|
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git |
|
cd /content/stable-diffusion-webui/ |
|
pip install -qq -r requirements.txt |
|
pip install -U xformers #Install `xformes` for better performance. |
|
``` |
|
|
|
```bash |
|
#Download model. |
|
wget https://huggingface.co/Ojimi/waifumake-full/resolve/main/waifumake-full-v2.safetensors -O /content/stable-diffusion-webui/models/Stable-diffusion/waifumake-full-v2.safetensors |
|
``` |
|
|
|
```bash |
|
#Run and enjoy ☕. |
|
cd /content/stable-diffusion-webui |
|
python launch.py --xformers |
|
``` |
|
|
|
- Try it in Google Colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1D6LNtXrpD2QfUx-d_yztWZVgTiDAyyAT?usp=sharing) |
|
## Tips: |
|
- The `masterpiece` and `best quality` tags are not necessary, as it sometimes leads to contradictory results, but if it is distorted or discolored, add them now. |
|
- The CGF scale should be 7.5 and the step count 28 for the best quality and best performance. |
|
- Use a sample photo for your idea. `Interrogate DeepBooru` and change the prompts to suit what you want. |
|
- You should use it as a supportive tool for creating works of art, and not rely on it completely. |
|
|
|
## Preview: v2 model |
|
![](preview1.png) |
|
![](preview2.png) |
|
![](preview3.png) |
|
![](preview4.png) |
|
- Enchance and Upscale using Stable Diffusion - Waifumake model v2 (⚠️Performance warning): I recommend against making the image too big as it can lead to unexpected problems. |
|
![](preview5.png) |
|
## Training: |
|
- **Data**: The model is trained based on a database of various sources from the Internet provided by my friend and images created by another AI. |
|
- **Schedule**: Euler Ancestral Discrete. |
|
- **Optimizer**: AdamW, xFormers |
|
- **Precision**: BF16. |
|
- **Hardware**: Google Colaboratory Pro - NVIDIA A100 40GB VRAM. |
|
|
|
## **Limitations:** |
|
- Loss of detail, errors, bad human-like (six-fingered hand) details, deformation, blurring, and unclear images are inevitable. |
|
- Complex tasks cannot be handled. |
|
- ⚠️Content may not be appropriate for all ages: As it is trained on data that includes adult content, the generated images may contain content not suitable for children (depending on your country there will be a specific regulation about it). If you do not want to appear adult content, make sure you have additional safety measures in place, such as adding "nsfw" to the negative prompt. |
|
- The results generated by the model are considered impressive. But unfortunately, currently, it only supports the English language, to use multilingual, consider using third-party translation programs. |
|
- The model is trained on the `Danbooru` and `Nai` tagging system, so the long text may result in poor results. |
|
- My amount of money: 0 USD =((. |
|
|
|
![](money-wallet.gif) |
|
|
|
## **Desires:** |
|
As it is a version made only by myself and my small associates, the model will not be perfect and may differ from what people expect. Any contributions from everyone will be respected. |
|
|
|
Want to support me? Thank you, please help me make it better. ❤️ |
|
|
|
## Special Thank: |
|
This wouldn't have happened if they hadn't made a breakthrough. |
|
- [Runwayml](https://huggingface.co/runwayml/): Base model. |
|
- [d8ahazard](https://github.com/d8ahazard/sd_dreambooth_extension) : Dreambooth. |
|
- [Automatic1111](https://github.com/AUTOMATIC1111/) : Web UI. |
|
- [Mikubill](https://github.com/Mikubill/): Where my ideas started. |
|
- Chat-GPT: Help me do crazy things that I thought I would never do. |
|
- Novel AI: Dataset images. An AI made me thousands of pictures without worrying about copyright or dispute. |
|
- Danbooru: Help me write the correct tag. |
|
- My friend and others. |
|
- And You 🫵❤️ |
|
|
|
## Copyright: |
|
|
|
This license allows anyone to copy, modify, publish, and commercialize the model, but please follow the terms of the GNU General Public License. You can learn more about the GNU General Public License at [here](LICENSE.txt). |
|
|
|
If any part of the model does not comply with the terms of the GNU General Public License, the copyright and other rights of the model will still be valid. |
|
|
|
All AI-generated images are yours, you can do whatever you want, but please obey the laws of your country. We will not be responsible for any problems you cause. |
|
|
|
Don't forget me. |
|
|
|
# Have fun with your waifu! (●'◡'●) |
|
|
|
![](cry.png) |
|
|
|
Like it? |