Text-to-image finetuning - Skiittoo/sd-cartoon-faces-model

This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the Skiittoo/cartoon-faces dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['[Cartoon face with sunglasses]']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("Skiittoo/sd-cartoon-faces-model", torch_dtype=torch.float16)
prompt = "[Cartoon face with sunglasses]"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 6
• Learning rate: 1e-05
• Batch size: 1
• Gradient accumulation steps: 4
• Image resolution: 512
• Mixed-precision: fp16