AI Models
What each model is good at, where it differs from the others, and what it costs to run.
Alibaba's Qwen-Image 2.0. One model for a new picture or an edit of up to three pictures, including long and multilingual type.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Qwen Image 2 is Alibaba's Qwen-Image 2.0, the Qwen image model that generates and edits in one model. Use it for a picture with a lot of type, or for an edit of pictures you already have.
The Qwen team describes Qwen-Image 2.0 as one model for high-fidelity generation and precise editing: long instructions, multilingual type, photoreal detail in texture and light, and more stable results across styles. It is built to follow a complicated prompt without dropping pieces of it.
Write the picture in the prompt. To edit, attach one to three pictures. There is no Enhance switch and no @ tag on this model.
Qwen is the first Qwen image model. It edits or transforms one picture, and the Qwen team built it around complex text. Qwen Image 2 takes up to three pictures in one edit.
Yes. One to three pictures, plus the prompt that says what should change.
No. @ tags are on other image models. Here you attach the pictures and describe the edit.
No. The prompt is used as you wrote it.
The first model takes one picture, either to edit or to transform. This one takes up to three, and the Qwen team describes it as the unified generator and editor.
