Text-to-image finetuning - nroggendorff/anime-girl-diffusion

This pipeline was finetuned from nroggendorff/epicrealism on the nroggendorff/grill dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['a grill with food on it']:

val_imgs_grid

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("nroggendorff/anime-girl-diffusion", torch_dtype=torch.float16)
prompt = "a grill with food on it"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

  • Epochs: 7500
  • Learning rate: 1e-05
  • Batch size: 16
  • Gradient accumulation steps: 1
  • Image resolution: 512
  • Mixed-precision: fp16

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]

Downloads last month
5
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for nroggendorff/anime-girl-diffusion

Base model

glides/epicrealism
Finetuned
(2)
this model