
480P, 720P or 1080P compares the three Wan tiers side by side.
Two places, one setting. In the episode editor: the button in the top bar that shows the current tier’s name, next to Composite. In Settings: Model Preferences → Video Model. Both change the same thing — the tier your next segments render on, in this project and in new ones. Segments already made keep the tier they were made with, and each version records it. The price on a segment’s generate button always shows the tier you are about to use.
If you have never changed the video tier, this is the one you are on.
Length: up to 30 seconds in one generation. That is the long-take mode; with the 15-second segment length a segment is at most 15 seconds. Resolution: 480P, in the aspect ratio of the project (16:9 or 9:16). Sound: spoken lines and ambient sound come out of the same generation as the picture; each character speaks in their own voice — the preset or uploaded voice if you set one, otherwise the written voice description. Cuts: a segment can contain several shots; the storyboard decides where they fall.
The tier reads the character sheets, location images and prop images for the assets named in the segment, plus voices and any state images you assigned. The limits are per generation:
10 credits per second of finished video. A 15-second segment is 15 × 10; a 30-second long take is twice that. For comparison, the same seconds at 720P cost 19 per second and at 1080P 38 per second. Regenerating a segment is a new charge each time; every version is kept, so nothing is lost by trying. Credits are only taken when the video is delivered.
Good at: drafting. Blocking a scene, checking that the right people are in frame, hearing how the lines land, finding out whether a 30-second take holds together. Most of what makes a shot right or wrong — who is in it, what they do, where the camera is — is visible at 480P.
Watch: fine detail (a pattern on a prop, embroidery, distant faces) is soft at 480P; that is what 720P and 1080P are for, not a reason to rewrite the storyboard. Dialogue in German and Ukrainian occasionally mispronounces a word on this tier; shorter sentences help, and a regeneration is cheap here.
Text and references are checked before rendering. A rejection is not charged: the credits come back and the credit history says so. The count is kept per account: after 12 rejections within 24 hours, the next one is held for review instead of refunded, and video generation pauses for 1 hour. So edit the flagged material rather than retrying the same segment. Content rules and checks explains what gets flagged.
The messages you are most likely to meet on this tier, what they mean and what to do:
| What you see | Usual cause | What to do |
|---|---|---|
| “Invalid input — check the reference images and duration, then retry.” | Usually one of the reference files for this segment could not be read | Generate again once; if it keeps failing, check that the character, location and prop images open, then contact support |
| “Blocked by content safety rules — edit the script or description and retry.” | The script or a reference tripped the content check | Edit the flagged part; see the content-check section for when a rejection is refunded |
| “The generation service hit a temporary problem. You weren’t charged — feel free to try again.” | The service was saturated; the site already tried again once for you | Wait a few minutes and generate again; nothing was deducted |
| Video generation paused | More than 12 rejected generations within 24 hours; the next one is held for review | Wait out the pause (1 hour); fix the material before retrying |
Up to 720P when a segment is right and you want it crisp for sharing. Up to 1080P for the version you will publish or cut into a longer film. Sideways to MiniMax H3 for a 2K picture, with its own reference rules; note it renders 15-second segments. Switching changes nothing in the storyboard: pick the tier, regenerate the segment, keep the version you like.
| Reference type | Limit on this tier | Note |
|---|---|---|
| Images | Up to 10 | Character sheets, location and prop images, states, your own uploads |
| Voice clips | Up to 5, about 14 s in total | Character voices; a clip that does not fit is left out and that character speaks from the written voice description |
Yes. Until you pick something else in the editor or in Settings, every segment renders on this tier.
No. Resolution is decided at generation. Pick the 1080P tier and regenerate the segment; the storyboard, references and voices stay exactly as they were.
No. The price is per second at the same rate; a 30-second take simply has twice the seconds of a 15-second one.
Usually one of the reference files for the segment could not be read. Generate again once; if it keeps failing, check that the character, location and prop images open, then contact support.
Generated with the picture. Lines are spoken in each character’s voice; ambient sound matches the scene.
Upload a script, generate the first scene on the default tier, and see the whole episode move before you spend on resolution.
Updated September 27, 2026
Pricing·Novel to Video·Guides·Samples·Support·Privacy·Terms·Legal·Contact·© 2026 SceneMixer