--- 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: ![Step 50](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_50.png) ![Step 100](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_100.png) ![Step 150](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_150.png) ![Step 200](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_200.png) ![Step 250](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_250.png) ![Step 300](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_300.png) ![Step 350](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_350.png) ![Step 400](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_400.png) ![Step 450](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_450.png) ![Step 500](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_500.png) ![Step 550](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_550.png) ![Step 600](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_600.png) ![Step 650](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_650.png) ![Step 700](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_700.png) ![Step 750](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_750.png) ![Step 800](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_800.png) ![Step 850](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_850.png) ![Step 900](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_900.png) ![Step 950](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_950.png) ![Step 1000](https://huggingface.co/Mou11209203/ddpm-celebahq-256/resolve/main/images/image_step_1000.png) ## 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: ```bash pip install torch diffusers safetensors ``` ### Loading the Model To load the model and run inference, you can use the following code: ```python 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](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb) ## 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: ```bibtex @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](https://www.apache.org/licenses/LICENSE-2.0).