pytorch-image-translation-models 0.2.4

A PyTorch library for multi-modal image translation with diffusion bridges, GANs, and transformer backbones.

pytorch-image-translation-models

A PyTorch library for multi-modal image translation with diffusion bridges, GANs, and transformer backbones.

Installation

Install from PyPI

pip install pytorch-image-translation-models

Install from source

pip install -e .

With optional dependencies:

# With training extras (accelerate, peft, datasets, tensorboard)
pip install -e ".[training]"

# With metrics extras (torchmetrics, lpips, torch-fidelity, scipy)
pip install -e ".[metrics]"

# Everything
pip install -e ".[all]"

Note: PyTorch is listed as a dependency but you may want to install a specific CUDA build first. See PyTorch — Get Started for details.

Quick Start

import src

gen = src.UNetGenerator(in_channels=3, out_channels=3)
disc = src.PatchGANDiscriminator(in_channels=6)

from src.training import Pix2PixTrainer, TrainingConfig
config = TrainingConfig(epochs=100, device="cuda")
trainer = Pix2PixTrainer(gen, disc, config)
trainer.fit(dataloader)  # expects {"source": tensor, "target": tensor}

translator = src.ImageTranslator(gen, device="cuda")
result = translator.predict(pil_image)

Documentation

Doc	Description
Features	Models, schedulers, pipelines, data, losses, training, metrics
Examples	Extended usage for I2SB, DDBM, UNSB, Local Diffusion, etc.
Package structure	Source layout and module overview
Credits	Reference papers and citations

License

MIT