Wan Video 2.5 Image to Video: the still is the contract (5s, 10s, 1080p, 15cr)

Wan Video 2.5 Image to Video is image-to-video. If the label is wrong, every second is waste.

Wan Video 2.5 Image to Video is high-quality image-to-video with Wan 2.5. Content type is video. Category is image-to-video. Requires an image. Audio is false. Durations: 5s and 10s. Max output: 1080p. Quality chips: 480p, 720p, 1080p. Frame rates: 24fps, 30fps, 60fps. Motion levels: Medium, High. Display price: 15 credits. The still is the brief. The model moves it.

Fifteen credits on a locked plate

15 credits is the display price for this I2V pass — not 62, not 110. Cheap enough to retry, not cheap enough to retry the wrong label. The label is image-to-video. No still, no generate. A paragraph where the image should be is a wrong label. Every second of the 5s or 10s is waste.

The AI image-to-video tool is the door. Image-to-video is the term. Best image-to-video model is the ranked list. Best Wan model is the family. The Wan roster also has a text-to-video sibling, Wan Video 2.5 T2V. That is a different slug. Do not paste a T2V prompt into this I2V row and hope.

Five seconds or ten, soundtrack off

audio is false. 5s and 10s come back silent. Prompting a voice line here does not buy dialogue. It may smear the plate with painted words. If you need a line, generate speech on a TTS row and lay it in the editor after this pass.

1080p is the ceiling. 480p and 720p are quality chips on the way up. Pick the quality the still can support. A soft plate at 1080p is a sharp view of softness.

24 / 30 / 60fps and Medium / High motion are extras on a locked still, not a substitute for the still. High motion on an unapproved composition is 10s of confident drift. Medium on an approved product still is often the whole job.

The still is the only brief

Composition, product, type, the face — all of that is decided before this row. Wan 2.5 I2V's description is "high-quality image-to-video." High quality is the motion pass. It is not a second chance at the layout.

If the still is not approved, stop. Edit the still. Then come back. The 15-credit generate will honor whatever you upload, including the extra hand and the wrong headline.

Styles listed: Cinematic, Documentary, Abstract. Those shift motion register. They do not unmute audio. They do not remove the image requirement.

If you wanted text-to-video, leave this slug

Wrong label, in practice: running the I2V slug without an image; expecting a 15s or 30s chip that does not exist; expecting native audio; expecting the model to invent the pack. Correct label: approved still, 5s or 10s, up to 1080p, silent, 15 credits, Wan 2.5 image-to-video.

The T2V vs I2V fork is which to use. For Wan 2.5, the fork is also two slugs. Pick the one whose input you actually have.

FAQ

Does Wan 2.5 Image to Video need a still?

Yes. requires_image is true. Category is image-to-video. If you only have text, use a text-to-video row such as Wan Video 2.5 T2V, or lock a still first.

Is there a soundtrack on this row?

No. audio is false. 5s or 10s, up to 1080p, 15 credits, silent. Mix speech after.

Can I generate 15s or 30s here?

No. Durations are 5s and 10s. A longer need is a different row or an extend pass, not a prompt trick on this slug.

What do the motion levels do?

Medium and High are motion-level chips on a locked still. They do not invent the plate. High on a wrong still is a more expensive wrong still.