metadata

license: creativeml-openrail-m
base_model: OFA-Sys/small-stable-diffusion-v0
datasets:
  - jwl25b/final_project_dataset
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
inference: true

Text-to-image finetuning - arpachat/stable-diffusion_unclip-small-v21-th-800-e4

This pipeline was finetuned from OFA-Sys/small-stable-diffusion-v0 on the jwl25b/final_project_dataset dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ["Tommy Hilfiger men's Regular Fit Round Logo Grey Polo"]:

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("arpachat/stable-diffusion_unclip-small-v21-th-800-e4", torch_dtype=torch.float16)
prompt = "Tommy Hilfiger men's Regular Fit Round Logo Grey Polo"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

Epochs: 400
Learning rate: 0.0001
Batch size: 8
Gradient accumulation steps: 4
Image resolution: 128
Mixed-precision: fp16

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