Text-to-image finetuning - ikozlov/sd-laion-art

This pipeline was finetuned from stabilityai/stable-diffusion-2-1 on the fantasyfish/laion-art dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A man in a suit']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("ikozlov/sd-laion-art", torch_dtype=torch.float16)
prompt = "A man in a suit"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 32
• Learning rate: 1e-05
• Batch size: 16
• Gradient accumulation steps: 4
• Image resolution: 512
• Mixed-precision: None

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