Text-to-image finetuning - gremlin97/RemoteDiff

This pipeline was finetuned from runwayml/stable-diffusion-v1-5 on the None dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A satellite image of a crop field']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("gremlin97/RemoteDiff", torch_dtype=torch.float16)
prompt = "A satellite image of a crop field"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 5
• Learning rate: 1e-06
• Batch size: 4
• Gradient accumulation steps: 4
• Image resolution: 224
• Mixed-precision: fp16

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