Image to video
Wan 3.0 Prime Image to Video
One photo in, motion and sound out — the cheapest full-quality option in the catalogue.
What it does
The speed-tuned tier of the 3.0 generation: half the per-second cost of the 2.7 row it replaces, generated audio on by default, and an optional end frame. The endpoint's own `duration` accepts null for a model-chosen length, but the product never sends it that way — a per-second row requires `durationSec` and clamps it to the 1-15s bounds above (`generic-run.ts`), because a length nobody chose cannot be quoted before the run.
What you give it
- Takes
- Image, Text prompt (optional)
- Produces
- video
- Length
- 1–15s
- Reference images
- 1
- Resolutions
- 480p, 720p, 1080p
- Aspect ratios
- adaptive, 16:9, 4:3, 1:1, 3:4, 9:16
- Audio
- generated with the video
- Category
- Image to video
- Price
- 5 cr / 5 s
Required: image. Anything else listed above is optional.
Wan 3.0 Prime Image to Video: common questions
What is Wan 3.0 Prime Image to Video best for?
Wan 3.0 Prime Image to Video is an image to video model. Start from a photo and let the model find the motion. One photo in, motion and sound out — the cheapest full-quality option in the catalogue. People run it for: cheap, end frame, native audio, 1080p.
How much does Wan 3.0 Prime Image to Video cost?
5 credits for a 5 s clip. It bills per second of output at 1 credit a second, so a shorter clip costs proportionally less. Billing stops at 15 seconds, so one run never costs more than 15 credits. Credits are the only unit we quote. One balance covers every model in the catalogue, so there is no subscription attached to Wan 3.0 Prime Image to Video specifically and no minimum spend to use it. See the pricing page for what a credit costs.
What do you need to give Wan 3.0 Prime Image to Video?
It accepts an image and a text prompt. It will not start without an image; everything else is optional. One reference image per run. Resolutions: 480p, 720p, 1080p. Aspect ratios: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16.
What do you get back from Wan 3.0 Prime Image to Video, and how long does a run take?
Every run returns one video. A single run gives you between 1 and 15 seconds. It produces the audio along with the picture. 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 We do not quote a fixed wall-clock time: it moves with the length of the run and with how busy the queue is.
How does Wan 3.0 Prime Image to Video compare with other image to video models?
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. They all draw on one credit balance, so trying a second one costs nothing beyond the run itself.
What people make with it
A model is a means, not the job. These are the outcomes this one is usually bought for, each with its own walkthrough.
Others that do the same job

HappyHorse 1.1 Image to Video
Image to video
Turns one photo into a talking, moving clip with its own audio.
- Price
- from 10 cr / 5 s
- Maximum length
- up to 15s
- Lip-sync
- lip-sync
Kling 3.0 Pro Image to Video
Image to video
Cinematic motion from a single frame, with generated sound.
- Price
- from 10 cr / 5 s
- Maximum length
- up to 15s
Kling O3 Pro Image to Video
Image to video
Animates the way from one frame to another.
- Price
- from 10 cr / 5 s
- Maximum length
- up to 15s