--- license: mit tags: - pytorch - diffusion - ddpm - image-generation - cifar10 datasets: - cifar10 --- # DDPM trained on CIFAR-10 A Denoising Diffusion Probabilistic Model (DDPM) trained on CIFAR-10 using distributed training across 6 V100 GPUs. ## Model Description - **Architecture -** U-Net with attention (128 base channels) - **Training -** 100 epochs on CIFAR-10 (50,000 images) - **Hardware -** 3 nodes × 2 V100-16GB GPUs - **Framework -** PyTorch DDP ## Training Details | Parameter | Value | |-----------|-------| | Batch Size | 64 per GPU (384 effective) | | Learning Rate | 2e-4 | | Timesteps | 1000 | | EMA Decay | 0.9999 | ## Usage ```python import torch from models import UNet, GaussianDiffusion model = UNet(in_channels=3, out_channels=3, base_channels=128, channel_mults=(1,2,2,2), num_res_blocks=2, attention_resolutions=(2,)) model.load_state_dict(torch.load("model_ema.pt")) model.eval() diffusion = GaussianDiffusion(timesteps=1000) samples = diffusion.sample(model, image_size=32, batch_size=16, channels=3) ``` ## Training Code [GitHub Repository](https://github.com/arvinsingh/Darkbird) ## Citation ```bibtex @misc{darkbird2026, author = {Arvin Singh}, title = {Darkbird: Distributed Training Examples}, year = {2026}, url = {https://github.com/arvinsingh/Darkbird} } ```