Modelpublic

Acadys/PointConImageModel

sourceHugging Facecreativeml-openrail-mupdated 3y agoView on Hugging Face

0likes6downloads

Model Card

Text-to-image finetuning - IUseAMouse/PointConImageModel

This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the IUseAMouse/PointConImages dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Un patron donne un dossier à un employé']:

[image]

Pipeline usage

You can use the pipeline like so:

python

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("IUseAMouse/PointConImageModel", torch_dtype=torch.float16)
prompt = "Un patron donne un dossier à un employé"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

—Epochs: 60
—Learning rate: 1e-05
—Batch size: 1
—Gradient accumulation steps: 4
—Image resolution: 512
—Mixed-precision: fp16

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