AI Models
What each model is good at, where it differs from the others, and what it costs to run.
Alibaba's Wan 2.7 image model. A new picture from a prompt, or an edit of one to four pictures. Wan 2.7 Image Pro is the sharper sibling.
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Wan 2.7 Image is Alibaba's Wan 2.7 stills model. Use it for a picture that should look like a specific person or product, or for an edit of pictures you already have.
Alibaba describes Wan 2.7-Image as a single model for text-to-image and instruction editing, aimed at personalized, high-fidelity pictures and at type that stays readable. It is the stills model in the Wan 2.7 line, not the video model.
Write the picture in the prompt. To edit, attach one to four pictures. There is no Enhance switch and no @ tag on this model.
Wan 2.7 Image Pro is the sibling Alibaba describes as more stable in composition and sharper at reading the prompt. Wan 2.7 makes video. This page makes the still.
Yes. One to four pictures, plus the prompt.
No. Attach them and describe the change. @ tags are on the Wan 2.7 video reference model.
Alibaba says Image Pro holds composition more steadily and reads the prompt more sharply. The way you attach pictures is the same.
No. Wan 2.7 is the clip. This is the still.
