AI Models
The models behind Visxy
What each model is good at, where it differs from the others, and what it costs to run.
AI Models
What each model is good at, where it differs from the others, and what it costs to run.
Google's fast Imagen 4. A text-to-image picture when you want the idea quickly. It does not take a picture to edit.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Imagen 4 Fast is Google's fast Imagen 4 model. Use it when you want a text-to-image picture quickly and you are not asking for the strictest match to a long prompt.
Google describes Fast as the Imagen 4 model built for speed, for rapid generation and high-volume work, beside Imagen 4 and Imagen 4 Ultra. It is still an Imagen 4 picture: detail and type, from words alone.
Write the picture in the prompt. There is no picture to attach.
Imagen 4 is the flagship. Imagen 4 Ultra is the one Google points at when the prompt must be followed tightly. Fast is the quick pass in the same family. None of the three edit.
No. Text only, like the rest of Imagen 4.
No. It is its own model.
When the picture has to follow a demanding prompt as closely as Google describes for Ultra, or when you want the flagship rather than the fast variant.
No. It can render type in a new picture. Editing a picture you already have is a different model.