ArcaneFace-Diffusion

arcaneface Diffusion

This is the fine-tuned Stable Diffusion model trained by dreambooth with 30k steps, images dataset from Arcane4K. Use the tokens arcaneface in your prompts for the effect.

🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion.

You can also export the model to ONNX, MPS and/or FLAX/JAX.

from diffusers import StableDiffusionPipeline
import torch
model_id = "michaelz/arcaneface-diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32)
pipe.requires_safety_checker = False
pipe.safety_checker = None
pipe = pipe.to("cuda")
prompt = "arcaneface, a beautiful girl"
image = pipe(prompt).images[0]
image.save("example.png")

Sample images from the model:

Version 1 (arcaneface-diffusion-30k): This model was trained by dreambooth by 30k steps,a dataset Arcane4K with more than 3400 pictures