MaxReynolds's picture
End of training
74d7b09
metadata
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
datasets:
  - MaxReynolds/Lee_Souder_Combined
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
inference: true

Text-to-image finetuning - MaxReynolds/SouderRocketLauncherNetCombined-v1-4-400

This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the MaxReynolds/Lee_Souder_Combined dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Rocket Launcher by Lee Souder']:

val_imgs_grid

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("MaxReynolds/SouderRocketLauncherNetCombined-v1-4-400", torch_dtype=torch.float16)
prompt = "Rocket Launcher by Lee Souder"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

  • Epochs: 40
  • Learning rate: 1e-05
  • Batch size: 1
  • Gradient accumulation steps: 4
  • Image resolution: 512
  • Mixed-precision: fp16

More information on all the CLI arguments and the environment are available on your wandb run page.