Scoresdeve Ema Multi Dsprites 64

🚀 Unconditional Image Generation with Diffusers

This project uses the Diffusers library to perform unconditional image generation. It leverages pre - trained models and datasets for generating images.

🚀 Quick Start

Prerequisites

First, ensure you have the necessary libraries installed. You can install the diffusers library using the following command:

# !pip install diffusers

Code Example

The following code demonstrates how to use the DiffusionPipeline to generate an image:

from diffusers import DiffusionPipeline
import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_id = "eurecom-ds/scoresdeve-ema-multi-dsprites-64"

# load model and scheduler
pipe = DiffusionPipeline.from_pretrained(model_id, trust_remote_code=True)
pipe.to(device)


# run pipeline in inference (sample random noise and denoise)
generator = torch.Generator(device=device).manual_seed(46)
image = pipe(
  generator=generator,
  batch_size=1,
  num_inference_steps=1000
).images


# save image
image[0].save("sde_ve_generated_image.png")

Generated Image

📦 Datasets and Libraries