Prompt-led direction
Describe subjects, action, camera movement, atmosphere and sound in a single production brief.
Wan 2.7 multimodal video
Choose text-to-video, image-to-video, reference-to-video or video editing. Add the inputs for your mode, select the output settings and follow the asynchronous result online.
Output
Your video will appear here
Choose a mode, add its required inputs and submit a Wan 2.7 task.
The model suite, explained
Wan 2.7 is a multimodal video generation suite for creating and transforming short videos from text, images and existing footage.
This workspace brings four practical workflows together: text-to-video, image-to-video with first and optional last frame guidance, reference-to-video for visual consistency, and prompt-led video editing.
Each request runs as an asynchronous Kie task. After completion, FramePack stores the output privately so you can preview and download it from the same workspace.
Four workflows, one page
Move from an original idea to a guided animation or targeted edit without changing tools.
Describe subjects, action, camera movement, atmosphere and sound in a single production brief.
Start from a first frame, add an optional final frame, guide consistency with references, or transform a source video.
Choose 720p or 1080p, a supported aspect ratio, and a mode-aware duration from 2 to 15 seconds; video edit can also preserve the source length.
Follow the provider task while it runs, then preview and download the privately stored result.
Three focused steps
Choose the workflow that matches your source material, give the model clear direction, and review the finished clip.
Start with text-to-video, image-to-video, reference-to-video or video edit according to the material you already have.
Write the prompt, upload the required media, then choose resolution, aspect ratio and duration.
Submit the task, follow its status, and open or download the finished video when processing completes.
Clear prompts and purposeful references make motion and edits easier to control.
Questions, answered
It supports text-to-video, first-frame and optional last-frame image-to-video, reference-to-video, and prompt-based editing of an uploaded video.
Image inputs accept JPG, PNG or WebP files. Reference-to-video accepts one to five MP4, MOV or image references in total; video edit accepts one MP4 or MOV source clip and an optional reference image.
Timing varies with resolution, duration and provider queue capacity. The page keeps checking the asynchronous Kie task while it runs.
After Kie returns the result, FramePack copies it into private media storage and provides authenticated preview and download links.
Choose a Wan 2.7 workflow, add clear visual direction, and create your next video online.
Create with Wan 2.7