Create from a prompt, animate frames, guide subjects with references, or edit an existing clip in 720P or 1080P.
Switch between Text, Image, Reference, and Video Edit. A 5-second standard generation is estimated at 300 credits in 720P or 400 credits in 1080P; reference and edit jobs show their own price before generation.
Open the generator when you are ready to upload a reference or write a prompt.
Open generatorThese existing vid2vid previews show input and output structure only. They are not Wan 2.7 outputs or vendor benchmark samples.
Use Video Edit to preserve recognizable motion while changing lighting, atmosphere, materials, and visual direction.
Transform this city walk into a cinematic rainy night while preserving the subject, walk cycle, framing, and camera path.
Use image animation, references, or Video Edit to direct a product toward a cleaner campaign finish.
Create a premium technology commercial with clean reflections, precise edge lighting, stable product detail, and restrained motion.
The generator selects the correct Wan endpoint for the input workflow instead of treating Wan 2.7 as one generic request.
Generate a new 720P or 1080P scene directly from a written prompt and aspect ratio.
Animate a first frame or control a transition with first and last frames.
Use up to five combined image and video references to guide subjects and creative identity.
Upload a source clip and describe local changes, style transfer, restoration, or visual cleanup.
The model-specific evidence is the connected KIE endpoint contract. The shared previews above only illustrate workflow shape and are not Wan 2.7 output samples.
Text uses wan/2-7-text-to-video and the prompt-first composer.
Image uses wan/2-7-image-to-video with first and optional last frame control.
Reference uses wan/2-7-r2v; source-video editing uses wan/2-7-videoedit.
Choose the mode according to what you already have and what must remain consistent.
Start from text for concepts, previsualization, social clips, and campaign directions.
Start from a still image or multiple references when visual identity matters.
Start from a video when timing and motion should remain recognizable while the finish changes.
The input type determines which Wan 2.7 endpoint the generator sends to.
Text creates a new scene, Image animates frames, Reference guides identity, and Video edits source footage.
The composer changes its upload controls and model automatically for the selected workflow.
Review 720P or 1080P, output duration, and the displayed credit cost before generating.
Answers about modes, references, resolution, and generation workflow.
Start from text, frames, references, or an existing video and review the exact price before creating the task.
