This pipeline was finetuned from stabilityai/stable-diffusion-2-base on the jytjyt05/t_to_m3 dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['C-Major, Piano, Solo, Ultra High Resolution']:

Pipeline usage

You can use the pipeline like so:

python

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("kerianheYi/CS245-fine-tunedSD1000_708", torch_dtype=torch.float16)
prompt = "C-Major, Piano, Solo, Ultra High Resolution"
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