|
--- |
|
language: |
|
- en |
|
thumbnail: "" |
|
tags: |
|
- painting |
|
- anime |
|
- stable-diffusion |
|
- aiart |
|
- text-to-image |
|
license: creativeml-openrail-m |
|
--- |
|
<center><img src="" width="512" height="512"/></center> |
|
|
|
 |
|
|
|
# DGSpitzer Art Diffusion |
|
|
|
An AI model that generates cyberpunk anime characters!~ |
|
|
|
Based of a [Vintedois diffusion-v0-1 Model](https://huggingface.co/22h/vintedois-diffusion-v0-1/), training in Dreambooth |
|
|
|
by [DGSpitzer](https://www.youtube.com/channel/UCzzsYBF4qwtMwJaPJZ5SuPg) |
|
|
|
### 🧨 Diffusers |
|
|
|
This repo contains both .ckpt and Diffuser model files. It's compatible to be used as any Stable Diffusion model, using standard [Stable Diffusion Pipelines](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion). |
|
|
|
You can convert this model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX](https://huggingface.co/blog/stable_diffusion_jax). |
|
|
|
```python example for loading the Diffuser |
|
#!pip install diffusers transformers scipy torch |
|
from diffusers import StableDiffusionPipeline |
|
import torch |
|
|
|
model_id = "DGSpitzer/DGSpitzer-Art-Diffusion" |
|
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "a beautiful mech girl, painting style, 4k, photorealistic" |
|
image = pipe(prompt).images[0] |
|
|
|
image.save("./dgspitzer_ai_art.png") |
|
``` |
|
|
|
# Online Demo |
|
|
|
You can try the Online Web UI demo build with [Gradio](https://github.com/gradio-app/gradio), or use Colab Notebook at here: |
|
|
|
*My Online Space Demo* |
|
[](https://huggingface.co/spaces/DGSpitzer/DGS-Diffusion-Space) |
|
|
|
*Buy me a coffee if you like this project ;P ♥* |
|
[](https://www.buymeacoffee.com/dgspitzer) |
|
|
|
<center><img src="" width="512" height="512"/></center> |
|
|
|
# **👇Model👇** |
|
|
|
AI Model Weights available at huggingface: https://huggingface.co/DGSpitzer/DGSpitzer-Art-Diffusion |
|
|
|
<center><img src="" width="512" height="512"/></center> |
|
|
|
# Usage |
|
|
|
After model loaded, use keyword **dgs** in your prompt, with **illustration style** to get even better results. |
|
|
|
For sampler, use **Euler A** for the best result (**DDIM** kinda works too), CFG Scale 7, steps 20 should be fine |
|
|
|
**Example 1:** |
|
|
|
``` |
|
portrait of a girl in dgs illustration style, Anime girl, female soldier working in a cyberpunk city, cleavage, ((perfect femine face)), intricate, 8k, highly detailed, shy, digital painting, intense, sharp focus |
|
``` |
|
|
|
For cyber robot male character, you can add **muscular male** to improve the output. |
|
|
|
**Example 2:** |
|
|
|
``` |
|
a photo of muscular beard soldier male in dgs illustration style, half-body, holding robot arms, strong chest |
|
``` |
|
|
|
**Example 3 (with Stable Diffusion WebUI):** |
|
|
|
If using [AUTOMATIC1111's Stable Diffusion WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) |
|
|
|
You can simply use this as **prompt** with **Euler A** Sampler, CFG Scale 7, steps 20, 704 x 704px output res: |
|
|
|
``` |
|
an anime girl in dgs illustration style |
|
``` |
|
|
|
And set the **negative prompt** as this to get cleaner face: |
|
|
|
``` |
|
out of focus, scary, creepy, evil, disfigured, missing limbs, ugly, gross, missing fingers |
|
``` |
|
|
|
This will give you the exactly same style as the sample images above. |
|
|
|
<center><img src="https://huggingface.co/DGSpitzer/Cyberpunk-Anime-Diffusion/resolve/main/img/ReadmeAddon.jpg" width="256" height="353"/></center> |
|
|
|
--- |
|
|
|
**NOTE: usage of this model implies accpetance of stable diffusion's [CreativeML Open RAIL-M license](LICENSE)** |
|
|
|
--- |
|
|
|
|
|
<center><img src="https://huggingface.co/DGSpitzer/Cyberpunk-Anime-Diffusion/resolve/main/img/4.jpg" width="700" height="700"/></center> |
|
|
|
<center><img src="https://huggingface.co/DGSpitzer/Cyberpunk-Anime-Diffusion/resolve/main/img/6.jpg" width="700" height="700"/></center> |
|
|
