---

Everything V2

Everything V2 is a fine-tuned model based on SD2.1. It was trained using ED2 on a dataset of around 300k images. Like other anime-style Stable Diffusion models, it also supports danbooru tags to generate images.

e.g. 1girl, white hair, blue eyes, cat ears, outdoors, city

SHOW IMAGE

---

How to download

Batch download

1. Install Git
2. Create a folder of your choice and right click → "Git bash here" and open a gitbash on the folder's directory.
3. Run the following commands in order.

git lfs install
git clone https://huggingface.co/TheRafal/everything-v2

4. Complete

Select and download

1. Go to the Files and versions tab in the Everything V2 repository
2. Select the model that you want to download and its yaml file
3. Download
4. Complete

---

Diffusers

This model can be used just like any other Stable Diffusion model.

You can also export the model to ONNX or MPS.

import torch
from torch import autocast
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained('TheRafal/everything', torch_dtype=torch.float32).to('cuda')

prompt = "masterpiece, 1girl, blonde hair, blue eyes, colorful, cumulonimbus clouds, lighting, short hair, city, hoodie, night"
with autocast("cuda"):
    image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5)["images"][0]  
    
image.save(prompt.replace(" ", "_") + ".png")

SHOW IMAGE

Anime Girl:

---

Examples

Below are some examples of images generated using this model:

SHOW IMAGES

Anime Girl:

1girl, red hair, blue eyes, short hair, jacket, winter clothes, scarf, outdoors, tokyo \(city\), snow, snowing, gloves, pants, looking at viewer, cowboy shot
Steps: 50, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 2436148258, Size: 768x768

Anime Boy:

1boy, black hair, green eyes, bishounen, casual, indoors, sitting, coffee shop, sitting, bokeh
Steps: 50, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 4225599226, Size: 768x768

---

License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here