You can deploy this model and start earning money today!

jonathandinu/
ddpm-ema-sfhq-256

Name: ddpm-ema-sfhq-256
Availability: InStock

Views

No views yet

grid of 4x2 images generated from the model

Model Card for `ddpm-ema-sfhq-256`

Unconditional DDPM diffusion model trained from scratch on part 4 of the SFHQ dataset of synthetic faces.

bash

accelerate launch train_unconditional.py \
  --train_data_dir="/notebooks/sfhq" \
  --resolution=256 --center_crop --random_flip \
  --output_dir="ddpm-ema-sfhq-256" \
  --train_batch_size=8 \
  --num_epochs=400 \
  --save_images_epochs=1 \
  --save_model_epochs=20 \
  --gradient_accumulation_steps=1 \
  --use_ema \
  --learning_rate=1e-4 \
  --lr_warmup_steps=500 \
  --resume_from_checkpoint="latest" \
  --mixed_precision="fp16" \
  --checkpoints_total_limit=5 \
  --checkpointing_steps=5000

Model Description

Developed and funded by: Jonathan Dinu
Model type: Unconditional DDPM diffusion model
License: non-commercial research and educational purposes
Training steps: 2,430,000 (155 epochs)
Resolution: 256x256 pixels

jonathandinu/ddpm-ema-sfhq-256

Model Card for ddpm-ema-sfhq-256

Model Description

jonathandinu/
ddpm-ema-sfhq-256

Model Card for `ddpm-ema-sfhq-256`