85244d4a59
In https://github.com/huggingface/diffusers/issues/124 I incorrectly suggested that the image set creation process was undocumented. In reality, I just hadn't located it. @patrickvonplaten did so for me. This PR places a hotlink so that people like me can be shoehorned over where they needed to be. |
||
|---|---|---|
| .. | ||
| README.md | ||
| train_unconditional.py | ||
README.md
Training examples
Creating a training image set is described in a different document.
Installing the dependencies
Before running the scipts, make sure to install the library's training dependencies:
pip install diffusers[training] accelerate datasets
Unconditional Flowers
The command to train a DDPM UNet model on the Oxford Flowers dataset:
accelerate launch train_unconditional.py \
--dataset="huggan/flowers-102-categories" \
--resolution=64 \
--output_dir="ddpm-ema-flowers-64" \
--train_batch_size=16 \
--num_epochs=100 \
--gradient_accumulation_steps=1 \
--learning_rate=1e-4 \
--lr_warmup_steps=500 \
--mixed_precision=no \
--push_to_hub
An example trained model: https://huggingface.co/anton-l/ddpm-ema-flowers-64
A full training run takes 2 hours on 4xV100 GPUs.
Unconditional Pokemon
The command to train a DDPM UNet model on the Pokemon dataset:
accelerate launch train_unconditional.py \
--dataset="huggan/pokemon" \
--resolution=64 \
--output_dir="ddpm-ema-pokemon-64" \
--train_batch_size=16 \
--num_epochs=100 \
--gradient_accumulation_steps=1 \
--learning_rate=1e-4 \
--lr_warmup_steps=500 \
--mixed_precision=no \
--push_to_hub
An example trained model: https://huggingface.co/anton-l/ddpm-ema-pokemon-64
A full training run takes 2 hours on 4xV100 GPUs.
