Wan 2.7 Image to Video

Wan 2.7 Image to Video is an image to video model. Start from a photo and let the model find the motion. One photo, an optional end frame or a voice track — Wan fills in the motion. People run it for: audio driven, continue clip, end frame.

10 credits for a 5 s clip. It bills per second of output at 2 credits a second, so a shorter clip costs proportionally less. Billing stops at 15 seconds, so one run never costs more than 30 credits. Credits are the only unit we quote. One balance covers every model in the catalogue, so there is no subscription attached to Wan 2.7 Image to Video specifically and no minimum spend to use it. See the pricing page for what a credit costs.

It accepts an image, a video, an audio track and a text prompt. One reference image per run. Resolutions: 720p, 1080p.

Every run returns one video. A single run gives you between 2 and 15 seconds. It produces the audio along with the picture. Speech is re-synced to the lips. Runs are queued and processed in the background, so you can close the tab — the finished file turns up in your library. We do not quote a fixed wall-clock time: it moves with the length of the run and with how busy the queue is.

The catalogue also runs HappyHorse 1.1 Image to Video (10 credits for a 5 s clip), Kling 3.0 Pro Image to Video (10 credits for a 5 s clip) and Kling O3 Pro Image to Video (10 credits for a 5 s clip) for the same job. HappyHorse 1.1 Image to Video is our default pick for image to video. This page documents a version the storefront no longer lists — Wan 3.0 Prime Image to Video has replaced it, and the model here still runs. They all draw on one credit balance, so trying a second one costs nothing beyond the run itself.