Text-to-image finetuning - yeonsikc/vae-model-finetuned
This pipeline was finetuned from runwayml/stable-diffusion-v1-5 on the yeonsikc/sample_repeat dataset. Below are some example images generated with the finetuned pipeline using the following prompts: Nothing:
Pipeline usage
You can use the pipeline like so:
from diffusers import DiffusionPipeline
import torch
pipeline = DiffusionPipeline.from_pretrained("yeonsikc/vae-model-finetuned", torch_dtype=torch.float16)
image = pipeline(prompt).images[0]
image.save("my_image.png")
Training info
These are the key hyperparameters used during training:
- Epochs: 100
- Learning rate: 2e-07
- Batch size: 1
- Gradient accumulation steps: 2
- Image resolution: 128
- Mixed-precision: fp16
More information on all the CLI arguments and the environment are available on your wandb
run page.