Edit model card

Anime Art Diffusion XL Model Card

Anime Art XL is a latent text-to-image diffusion model capable of generating images of people, mainly, and other things, in the style of Japanese anime. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion blog.

You can use this with the 🧨Diffusers library from Hugging Face.

So pretty, right?

Diffusers

from diffusers import StableDiffusionXLPipeline
import torch

pipeline = StableDiffusionXLPipeline.from_pretrained("nroggendorff/animexl").to("cuda")

image = pipeline(prompt="hatsune miku").images[0]
image.save("anime.png")

Model Details

  • train_batch_size: 1
  • gradient_accumulation_steps: 4
  • learning_rate: 1e-2
  • lr_warmup_steps: 500
  • mixed_precision: "fp16"
  • eval_metric: "mean_squared_error"

Limitations

  • The model does not achieve perfect drawing photorealism
  • The model cannot render legible text

Developed by

  • Noa Linden Roggendorff

This model card was written by Noa Roggendorff and is based on the Stable Diffusion v1-5 Model Card.

Downloads last month
28
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for glides/animexl

Adapters
1 model

Spaces using glides/animexl 2

Collection including glides/animexl