Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,128 @@
+# 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/{repo_name}/blob/main/images/image_step_50.png)
+![Step 100](https://huggingface.co/{repo_name}/blob/main/images/image_step_100.png)
+![Step 150](https://huggingface.co/{repo_name}/blob/main/images/image_step_150.png)
+![Step 200](https://huggingface.co/{repo_name}/blob/main/images/image_step_200.png)
+![Step 250](https://huggingface.co/{repo_name}/blob/main/images/image_step_250.png)
+![Step 300](https://huggingface.co/{repo_name}/blob/main/images/image_step_300.png)
+![Step 400](https://huggingface.co/{repo_name}/blob/main/images/image_step_400.png)
+![Step 500](https://huggingface.co/{repo_name}/blob/main/images/image_step_500.png)
+![Step 600](https://huggingface.co/{repo_name}/blob/main/images/image_step_600.png)
+![Step 700](https://huggingface.co/{repo_name}/blob/main/images/image_step_700.png)
+![Step 800](https://huggingface.co/{repo_name}/blob/main/images/image_step_800.png)
+![Step 900](https://huggingface.co/{repo_name}/blob/main/images/image_step_900.png)
+![Step 1000](https://huggingface.co/{repo_name}/blob/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
+repo_id = "google/ddpm-celebahq-256"
+model = UNet2DModel.from_pretrained(repo_id, use_safetensors=True)
+model.to("cuda")  # Move the model to GPU
+display(model.config)
+
+# 2. Initialize the scheduler
+scheduler = DDPMScheduler.from_pretrained(repo_id)
+
+# 3. Create an image with Gaussian noise
+torch.manual_seed(0)  # Set random seed for reproducibility
+noisy_sample = torch.randn(1, model.config.in_channels, model.config.sample_size, model.config.sample_size).to("cuda")
+display(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])
+    display(f"Image at step {i}")
+    display(image_pil)
+
+# 5. Reverse diffusion process
+sample = noisy_sample
+for i, t in enumerate(tqdm.tqdm(scheduler.timesteps)):
+    # 1. Predict 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)
+
+display("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).