JoliGEN: Generative AI Toolset with GANs and Diffusion for Real-World Applications

JoliGEN provides easy-to-use generative AI for image to image transformations.

Main Features

  • JoliGEN support both GAN and Diffusion models for unpaired and paired image to image translation tasks, including domain and style adaptation with conservation of semantics such as image and object classes, masks, ...

  • JoliGEN generative capabilities are targeted at real world applications such as Augmented Reality, Dataset Smart Augmentation and object insertion, Synthetic to real transforms.

  • JoliGEN allows for fast and stable training with astonishing results. A server with REST API is provided that allows for simplified deployment and usage.

  • JoliGEN has a large scope of options and parameters. To not get overwhelmed, start with Quick Start. There are then links to more detailed documentation on models, dataset formats, and data augmentation.

Use cases

  • AR and metaverse: replace any image element with super-realistic objects

  • Smart data augmentation: test / train sets augmentation

  • Image manipulation: seamlessly insert or remove objects/elements in images

  • Image to image translation while preserving semantic, e.g. existing source dataset annotations

  • Simulation to reality translation while preserving elements, metrics, ...

  • Image to image translation to cope with scarce data

This is achieved by combining conditioned generator architectures for fine-grained control, bags of discriminators, configurable neural networks and losses that ensure conservation of fundamental elements between source and target images.

Example results

Image translation while preserving the class

Mario to Sonic while preserving the action (running, jumping, ...)

Object insertion

Car insertion (BDD100K) with Diffusion

Glasses insertion (FFHQ) with Diffusion

Object removal

Glasses removal with GANs

Style transfer while preserving label boxes (e.g. cars, pedestrians, street signs, ...)

Day to night (BDD100K) with Transformers and GANs

Clear to snow (BDD100K) by applying a generator multiple times to add snow incrementally

Clear to overcast (BDD100K)

Clear to rainy (BDD100K)


JoliGEN is created and maintained by Jolibrain.

Code is making use of pytorch-CycleGAN-and-pix2pix, CUT, AttentionGAN, MoNCE among others.

Some elements from JoliGEN are supported by the French National AI program "Confiance.AI"