vae-model-finetuned / README.md
mobled37's picture
End of training
347215b verified
metadata
license: creativeml-openrail-m
base_model: None
datasets:
  - vipseg
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
inference: true

Text-to-image finetuning - mobled37/vae-model-finetuned

This pipeline was finetuned from None on the vipseg dataset. Below are some example images generated with the finetuned pipeline using the following prompts: Nothing:

Training info

These are the key hyperparameters used during training:

  • Epochs: 1000
  • Learning rate: 1.92e-05
  • Batch size: 64
  • Gradient accumulation steps: 2
  • Image resolution: 30
  • Mixed-precision: fp16

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