Cyberpunk Anime Diffusion

🚀 Cyberpunk Anime Diffusion

An AI model that generates cyberpunk anime characters!

This AI model is designed to generate captivating cyberpunk anime characters. It is based on a finetuned Waifu Diffusion V1.3 Model with Stable Diffusion V1.5 New Vae, and was trained in Dreambooth by DGSpitzer.

✨ Features

• Model Compatibility: 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.
• Model Conversion: You can convert this model to ONNX, MPS and/or FLAX/JAX.

📦 Installation

This model requires the following Python libraries:

#!pip install diffusers transformers scipy torch

💻 Usage Examples

Basic Usage

# example for loading the Diffuser
from diffusers import StableDiffusionPipeline
import torch
model_id = "AdamOswald1/Cyberpunk-Anime-Diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a beautiful perfect face girl in dgs illustration style, Anime fine details portrait of school girl in front of modern tokyo city landscape on the background deep bokeh, anime masterpiece, 8k, sharp high quality anime"
image = pipe(prompt).images[0]
image.save("./cyberpunk_girl.png")

Advanced Usage

After the model is loaded, use the keyword dgs in your prompt, along with illustration style to get even better results. For the sampler, use Euler A for the best result (DDIM also works to some extent). A CFG Scale of 7 and 20 steps should be sufficient.

Example 1: Generate a girl portrait

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

Example 2: Generate a cyber robot male character You can add muscular male to improve the output.

a photo of muscular beard soldier male in dgs illustration style, half-body, holding robot arms, strong chest

Example 3: Using with Stable Diffusion WebUI If using AUTOMATIC1111's Stable Diffusion WebUI, you can simply use this as the prompt with the Euler A Sampler, a CFG Scale of 7, 20 steps, and a 704 x 704px output resolution:

an anime girl in dgs illustration style

And set the negative prompt as follows to get a cleaner face:

out of focus, scary, creepy, evil, disfigured, missing limbs, ugly, gross, missing fingers

📚 Documentation

Online Demo

• You can try the Online Web UI demo built with Gradio, or use the Colab Notebook:
  • My Online Space Demo
  • Finetuned Diffusion WebUI Demo by anzorq
  • Colab Notebook

Model Weights

AI Model Weights are available at Hugging Face: https://huggingface.co/AdamOswald1/Cyberpunk-Anime-Diffusion

📄 License

⚠️ Important Note

Usage of this model implies acceptance of Stable Diffusion's CreativeML Open RAIL - M license