Our Products

Francophone ? Cette vidéo en français présente notre plateforme https://dreamlook.ai, qui vous permets de créer des images et d’entrainer des modèles de génération d’images sur mesure :


Finetune Stable Diffusion in Minutes

With dreamlook.ai, we revolutionize how quickly and efficiently Stable Diffusion models can be trained.


We made it super easy to craft high-quality Stable Diffusion models and to generate high resolution images at lightning speed. Our Dreambooth API is optimized for robust scalability and user-friendliness. We’ve thrown in some cool features like LoRA file extraction and a heap of training options to play with.



Create Beautiful Art from Text

With diffusion.gg, we’re turning text into awesome images using Discord.

diffusion.gg screenshot

Just type “/draw” in our Discord chat, let your imagination run wild with prompts like “a horse in space,” and watch as unique, original images pop up right in your chat, thanks to the magic of Stable Diffusion. And the best part? You get started with 50 free images and keep the fun going with five more daily, all for free! Simply join the diffusion.gg Discord server and let the creative good times roll.



AI-generated Photorealistic Image Gallery

Nyx.gallery was our first venture into the world of AI-generated imagery.

nyx.gallery screenshot

Nyx.gallery was a mission to outdo regular stock photography by offering a vast and ever-growing selection of high-quality, photorealistic images. All these images were uniquely crafted using a mix of diffusion models and GANs, ensuring they’re not just rehashes of existing web content (yes, we checked with Google Reverse Image Search!). Whether it’s for a commercial project or just for fun, those are free to use as you please.


Our Research

“This Food Does Not Exist”

Training StyleGAN2 on TPUs in JAX

Generated cookie images

“This Food Does Not Exist” was our tasty twist on AI, where we’ve trained StyleGAN2 models to cook up synthetic, mouth-watering food pictures. In collaboration with EPFL’s Digital Epidemiology Lab and their Food & You project, we explored how synthetic data can boost vision tasks. You can check out our code and pretrained models, and even try creating your own food images with our Colab notebook.


Our Team

Martin and Florian

AI-generated image of the team

Martin Müller

Website / LinkedIn / Twitter

Florian Laurent

Website / LinkedIn / Twitter

In the news

Our supporters

Wingman Campus Fund FIT Digital La Forge Trust Village


Reach out to us at [email protected]

LinkedIn / Twitter