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.
Alibaba's Qwen Image 2.1. A new picture or an edit of up to four pictures, with Enhance if you want the prompt expanded.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Qwen Image 2.1 is Alibaba's Qwen image model for a new picture or an edit, in one model. Use it when a person or a product should stay recognizable, or when words in the frame have to read.
Its documentation describes Qwen Image 2.1 as a compact model that both generates and edits: readable type, and edits that keep people and products looking like themselves.
Write the picture in the prompt. Enhance is off until you turn it on; it lets the model expand the prompt before it generates. To edit, attach one to four pictures.
Qwen Image 2 edits up to three pictures and has no Enhance switch. Qwen takes one picture, either to edit or to transform. Qwen Image 2.1 takes up to four, and Enhance is available.
Yes. One to four pictures, plus the prompt.
It expands the prompt before generation. It stays off unless you turn it on.
No. Attach the pictures and describe the edit.
Qwen Image 3 and Qwen Image 3 Pro take one picture to edit. This model takes up to four.