Cool Japan Diffusion 2.1.1.1 Model Card

Introduction

Cool Japan Diffusion is the latent diffusion model created from Stable Diffsion. Cool Japan Diffusion is suitable for genetrating Cool Japan images such as Anime, Manga, and Game.

Legal and ethical information

We create this model legally. However, we think that this model have ethical problems. Therefore, we cannot use the model for commercially except for news reporting.

TBA.

Usage

You can try the model by our Space. I recommend to use the model by Web UI. You can download the model here. Safetensor version is here. Japanese manual is here.

Model Details

Developed by: Robin Rombach, Patrick Esser, Alfred Increment
Model type: Diffusion-based text-to-image generation model
Language(s): English
License: CreativeML Open RAIL++-M-NC License
Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses a fixed, pretrained text encoder (OpenCLIP-ViT/H).
Resources for more information: GitHub Repository.

Cite as:

@InProceedings{Rombach_2022_CVPR,
    author    = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
    title     = {High-Resolution Image Synthesis With Latent Diffusion Models},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {10684-10695}
}

Examples

Web UI
Diffusers

Web UI

Run with --no-half option. I recommend to install xformers. Download the model here. Then, install Web UI by AUTIMATIC1111.

Diffusers

Using the 🤗's Diffusers library to run Cool Japan Diffusion 2.1.1 Beta in a simple and efficient manner.

pip install --upgrade git+https://github.com/huggingface/diffusers.git transformers accelerate scipy

Running the pipeline (if you don't swap the scheduler it will run with the default DDIM, in this example we are swapping it to EulerDiscreteScheduler):

from diffusers import StableDiffusionPipeline, EulerAncestralDiscreteScheduler
import torch

model_id = "aipicasso/cool-japan-diffusion-2-1-2-beta"

scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "anime, masterpiece, a portrait of a girl, good pupil, 4k, detailed"
negative_prompt="deformed, blurry, bad anatomy, bad pupil, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, bad hands, fused fingers, messy drawing, broken legs censor, low quality, mutated hands and fingers, long body, mutation, poorly drawn, bad eyes, ui, error, missing fingers, fused fingers, one hand with more than 5 fingers, one hand with less than 5 fingers, one hand with more than 5 digit, one hand with less than 5 digit, extra digit, fewer digits, fused digit, missing digit, bad digit, liquid digit, long body, uncoordinated body, unnatural body, lowres, jpeg artifacts, 3d, cg, text, japanese kanji"
images = pipe(prompt,negative_prompt=negative_prompt, num_inference_steps=20).images
images[0].save("girl.png")

Notes:

Despite not being a dependency, we highly recommend you to install xformers for memory efficient attention (better performance)
If you have low GPU RAM available, make sure to add a pipe.enable_attention_slicing() after sending it to cuda for less VRAM usage (to the cost of speed)

*This model card was written by: Alfred Increment and is based on the Stable Diffusion v2