metadata

tags:
  - pytorch
  - diffusers
  - unconditional-image-generation
  - image-generation
  - denoising-diffusion
  - stable-diffusion
license: apache-2.0
library_name: diffusers
model_name: ddpm-celebahq-256

DDPM CelebAHQ 256 with Safetensors

This repository contains a denoising diffusion probabilistic model (DDPM) trained on the CelebA HQ dataset at a resolution of 256x256. The model is based on the original google/ddpm-celebahq-256 implementation and has been updated to support safetensors for model storage.

Model Information

Model Type: UNet2DModel
Diffusion Process: DDPM (Denoising Diffusion Probabilistic Models)
Training Data: CelebA HQ dataset
Resolution: 256x256
Format: The model weights are available in both safetensors and standard PyTorch (.pth) formats.

Features

Safetensors Support: The model weights are stored in the safetensors format, a safer and more efficient alternative to regular PyTorch .pth files. It ensures better compatibility, security, and serialization of model weights.
Pretrained Model: This model is pretrained on the CelebA HQ dataset and is designed for high-quality image generation.
Model Formats: Available in both standard PyTorch and safetensors formats for easy integration into your workflow.

Example Images

Here are some sample images generated by the model at different diffusion steps:

How to Use

To use this model, you can load it using the diffusers library from Hugging Face. You can load the model in either safetensors format or the traditional .pth format.

Requirements

Install the required dependencies:

pip install torch diffusers safetensors

Loading the Model

To load the model and run inference, you can use the following code:

import torch
import numpy as np
import PIL.Image
from diffusers import UNet2DModel, DDPMScheduler
import tqdm

# 1. Initialize the model
# Choose a model ID, use google's with use_safetensors=False, use Mou11209203's with use_safetensors=True
repo_id = "google/ddpm-celebahq-256"
repo_id1 = "Mou11209203/ddpm-celebahq-256"
model = UNet2DModel.from_pretrained(repo_id1, use_safetensors=True)
model.to("cuda")  # Move the model to GPU
print("model.config: ", model.config)

# 2. Initialize the scheduler
scheduler = DDPMScheduler.from_pretrained(repo_id1)
print("scheduler.config: ", scheduler.config)

# 3. Create an image with Gaussian noise
torch.manual_seed(1733783271)  # Fix the random seed for reproducibility
noisy_sample = torch.randn(1, model.config.in_channels, model.config.sample_size, model.config.sample_size).to("cuda")
print(f"Noisy sample shape: {noisy_sample.shape}")

# 4. Define a function to display the image
def display_sample(sample, i):
    image_processed = sample.cpu().permute(0, 2, 3, 1)
    image_processed = (image_processed + 1.0) * 127.5
    image_processed = image_processed.numpy().astype(np.uint8)

    image_pil = PIL.Image.fromarray(image_processed[0])
    print(f"Image at step {i}")
    image_pil.show()

# 5. Reverse diffusion process
sample = noisy_sample
for i, t in enumerate(tqdm.tqdm(scheduler.timesteps)):
    # 1. Predict the noise residual
    with torch.no_grad():
        residual = model(sample, t).sample

    # 2. Compute the less noisy image and move x_t -> x_t-1
    sample = scheduler.step(residual, t, sample).prev_sample

    # 3. Optionally display the image (every 50 steps)
    if (i + 1) % 50 == 0:
        display_sample(sample, i + 1)

print("Denoising complete.")

Training

If you want to train your own model, please have a look at the official training example

Model Storage

The following files are available for download:

Model Weights (PyTorch format): diffusion_pytorch_model.pth
Model Weights (Safetensors format): diffusion_pytorch_model.safetensors
Generated Images: Various steps from 50 to 1000
README.md: This document for usage and setup instructions

Citation

If you use this model in your research or project, please cite the original google/ddpm-celebahq-256 repository:

@misc{google/ddpm-celebahq-256,
  author = {Google Research},
  title = {DDPM CelebAHQ 256},
  year = {2022},
  url = {https://huggingface.co/google/ddpm-celebahq-256}
}

License

This model is provided under the Apache 2.0 License.