ddpm-apes-128

Model description

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

Intended uses & limitations

How to use

from diffusers import DDPMPipeline
import torch

model_id = "dn-gh/ddpm-apes-128"
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# load model and scheduler
ddpm = DDPMPipeline.from_pretrained(model_id).to(device) 

# run pipeline in inference
image = ddpm().images[0]

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

Limitations and bias

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

Training data

This model is trained on 4866 images generated with ykilcher/apes for 30 epochs.

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