kerianheYi's picture
End of training
94a39c8
metadata
license: creativeml-openrail-m
base_model: kerianheyi/CS245-fine-tunedSD8200_8600_14122
datasets:
  - jytjyt05/t_to_m7
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
inference: true

Text-to-image finetuning - kerianheYi/CS245-fine-tunedSD8600_9000_14122

This pipeline was finetuned from kerianheyi/CS245-fine-tunedSD8200_8600_14122 on the jytjyt05/t_to_m7 dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A melSpectrogram for piano solo in Major']:

val_imgs_grid

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("kerianheYi/CS245-fine-tunedSD8600_9000_14122", torch_dtype=torch.float16)
prompt = "A melSpectrogram for piano solo in Major"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

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