Text-to-image finetuning - GabrielGaleana34/sd-model-finetuned

This pipeline was finetuned from stabilityai/stable-diffusion-2-1 on the GabrielGaleana34/Products dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['[A Coca-cola soda in a plastic bottle]']:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("GabrielGaleana34/sd-model-finetuned", torch_dtype=torch.float16)
prompt = "A Coca-cola soda in a plastic bottle"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Epochs: 89
• Learning rate: 1e-06
• Batch size: 1
• Gradient accumulation steps: 4
• Image resolution: 1024
• Mixed-precision: fp16