AI video generator

One prompt box, two frontier models, three ways in: write a shot from nothing, animate a still you already have, or lock in the characters you want to keep. Pick a mode, hit render, and a finished clip lands in about a minute.

장면을 설명하세요: 피사체, 동작, 카메라 움직임, 조명. 키워드를 길게 나열하는 것보다 두세 문장이 낫습니다.

이 모델은 모든 영상에 동기화된 오디오 트랙을 렌더링합니다. 따로 켤 필요가 없습니다.

13 크레딧

신규 계정은 무료 크레딧 20개로 시작합니다. 이 설정으로 1회 렌더링할 수 있습니다. 요금

이 모델로 만든 영상

아래 영상은 모두 이곳에서 렌더링했으며, 영상 아래에 표시된 설정을 그대로 썼습니다. 캡션은 영상을 만든 프롬프트 원문입니다.

A ceramic pour-over kettle tips over a glass carafe and coffee falls in a thin dark ribbon; steam curls through a shaft of morning window light. Slow push-in, shallow depth of field, warm film grade.

Seedance 2.0 · 720p · 16:9 · 4s

A neon-lit ramen counter at night: steam rises off a fresh bowl as the chef slides it across the wood, reflections shifting in the window behind. Slow lateral dolly, shallow depth of field, cool blues against warm lamp light.

Seedance 2.5 · 720p · 16:9 · 4s

A lone red kayak cuts across a glassy alpine lake at dawn; mist lifts off the water and the mountains catch the first light. Slow aerial orbit, cinematic wide shot.

MiniMax H3 · 2K · 16:9 · 5s

The lid of the case lifts open, droplets slide off the shell, and the rim light sweeps across the wet surface as the camera pushes in.

Seedance 2.0 · 720p · 16:9 · 4s

The cat lifts its head, ears turning toward the window, then settles back into the sunbeam as the curtain stirs. Slow push-in, dust drifting through the light.

Seedance 2.5 · 720p · 16:9 · 4s

The cat stretches, blinks awake and settles back down; dust motes drift slowly through the sunbeam. Gentle handheld drift.

MiniMax H3 · 2K · 16:9 · 5s

The speckled teal mug sits on a wooden cafe counter with steam rising from it; a hand slides it forward into frame. Warm morning light, shallow focus.

Seedance 2.0 · 720p · 16:9 · 4s

The mug from @Image1 and the paper crane from @Image2 share a wooden desk beside a window; steam curls off the mug while the crane trembles in the draft. Slow dolly right, warm afternoon light, shallow focus.

Seedance 2.5 · 720p · 16:9 · 4s

The coral origami crane unfolds its wings and lifts off a wooden desk, drifting past a window into the evening light. Smooth tracking shot.

MiniMax H3 · 2K · 16:9 · 5s

From prompt to clip

  1. Pick a mode

    Text to video invents the scene. Image to video animates a frame you already have. Reference to video keeps a face, a product or a style consistent across shots.

  2. Set the shot

    Choose duration, resolution and aspect ratio. The cost in credits updates as you go, so nothing about the bill is a surprise.

  3. Render and download

    The job runs on our GPUs and streams progress into the panel beside the form. Finished clips are MP4, ready to post, and they stay in your library.

사양 한눈에 보기

모델길이해상도네이티브 오디오참조 이미지시작가
Seedance 2.04~15초480p · 720p · 1080p · 4K예최대 9장5초 기준 31 크레딧
Seedance 2.0 Mini4~15초480p · 720p예최대 9장5초 기준 19 크레딧
Seedance 2.54~30초480p · 720p예최대 30장5초 기준 58 크레딧
MiniMax H35~15초2K아니요최대 9장5초 기준 130 크레딧
MiniMax H3 Max Turbo5~15초480p · 768p예사용 안 함5초 기준 13 크레딧
MiniMax H3 Max5~15초480p · 768p예사용 안 함5초 기준 25 크레딧

Prompts that survive first contact

Name the camera. “Slow push in”, “handheld follow” or “locked-off wide” does more work than any adjective.

Give the light a direction. Backlit, golden hour, a single practical lamp — models track light far better than mood words.

One action per clip. Five seconds fits a single beat; stacking three actions gets you three half-actions.

Draft cheap, finish expensive. Find the shot at 480p or 720p, then re-render the keeper at full resolution.

Before you spend a credit