Update README.md

README.md

@@ -22,31 +22,30 @@ on the `Norod78/EmojiFFHQAlignedFaces` dataset.
 #### How to use
 
 ```python
-# TODO: add an example code snippet for running this diffusion pipeline
-```
+from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline
+
+
+def main():
+    model_id = "./ddpm-EmojiAlignedFaces-64"
 
-#### Limitations and bias
+    # load model and scheduler
+    ddpm = DDPMPipeline.from_pretrained(model_id)  # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference
 
-[TODO: provide examples of latent issues and potential remediations]
+    # run pipeline in inference (sample random noise and denoise)
+    image = ddpm()["sample"]
+
+    # save image
+    image[0].save("ddpm_generated_image.jpg")
+    image[0].show()
+
+if __name__ == '__main__':
+    main()
+```
 
-## Training data
 
 [TODO: describe the data used to train the model]
 
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 16
-- eval_batch_size: 16
-- gradient_accumulation_steps: 1
-- optimizer: AdamW with betas=(None, None), weight_decay=None and epsilon=None
-- lr_scheduler: None
-- lr_warmup_steps: 500
-- ema_inv_gamma: None
-- ema_inv_gamma: None
-- ema_inv_gamma: None
-- mixed_precision: fp16
+[Norod78/EmojiFFHQAlignedFaces](https://huggingface.co/datasets/Norod78/EmojiFFHQAlignedFaces)
 
 ### Training results