uumlaut / ddpm-vangogh-128

ddpm-vangogh-128

Model description

This diffusion model is trained with the 🤗 Diffusers library on the imagefolder dataset.

Intended uses & limitations

How to use

# !pip install diffusers
from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline

model_id = "uumlaut/ddpm-vangogh-128"

# load model and scheduler
ddpm = DDPMPipeline.from_pretrained(model_id)  # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference

# run pipeline in inference (sample random noise and denoise)
image = ddpm().images[0]

# save image
image.save("ddpm_generated_image.png")

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

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

Training results

📈 TensorBoard logs