Text to image (text2img)

Text to image, or text2img, is the core way an AI image model works: you write a prompt describing what you want to see, and the model generates a new picture from scratch to match it. There is no starting image involved, the whole scene, subject and style come from the words you type, plus any settings like size or seed.

It is the standard entry point for creating original artwork, portraits or concept images with a model like Stable Diffusion XL.

In tendre.AI, text2img is the default generation mode, running fully on your own NVIDIA GPU so every image stays private.

Related tutorial