MiniMax 海螺 H3（海螺 AI 的视频模型，也叫 Hailuo 3）是 MiniMax 在 2026 年 7 月 31 日发布的视频模型，能用文字、一张图片或几张参考图生成 5 到 15 秒、带立体声的视频。zzo.ai 上有两个版本：MiniMax 官方的 MiniMax H3，和一家独立 AI 公司用 MiniMax 开放权重做的 H3 Max Turbo，后者更快、更便宜。
5–15 秒
最高 2K
自带声音
这段视频用的提示词。可以直接改，也可以自己写。
带声音
用 海螺 H3 生成的
每个都写了提示词、模型和在这里生成要花多少。选一个，从它开始改。
“Medium close-up, 50mm. A night-market noodle vendor in a white apron stands behind a steaming wok under bare hanging bulbs. He looks into the camera and says: "Thirty years. Same pan, same recipe." Then he tosses the noodles high and flames jump up from the wok. Camera: gentle living handheld that barely breathes, slight push-in. Audio: his voice, sizzling oil, crowd chatter, distant scooters. Photorealistic, warm practical light.”MiniMax H3, 10 秒, 有声, 80 积分
“A chef in her forties looks straight into the camera in a bright open kitchen and says, "The secret is you never crowd the pan." She smiles and turns back to the stove. Clean daylight from a window, white tile, flour on her apron, a strand of hair loose. Medium close-up, 50mm, slight handheld. Sound: her voice close and clear, a gentle sizzle, a knife on a board off screen.”MiniMax H3, 5 秒, 有声, 40 积分
“Stop-motion claymation: a round green frog in a knitted scarf carries a stack of pancakes across a tiny kitchen set, sets it down, then looks at camera and blinks. Visible fingerprints in the clay, felt walls, warm practical lamps, stepped 12fps motion. Sound: playful pizzicato strings, soft clay squeaks, a plate clink.”MiniMax H3, 5 秒, 有声, 40 积分
“Macro shot of espresso pulling from a chrome portafilter into a warm glass, thick golden crema blooming and swirling. Bright morning light through a cafe window, steam curling, water spots on the chrome, a few coffee grounds on the tray. 100mm macro, shallow focus, slight handheld drift. Sound: grinder winding down, the hiss of the pump, liquid pattering into glass, cafe chatter behind.”MiniMax H3, 5 秒, 有声, 40 积分
“Two heavy draft horses stand together in a shallow flooded pasture at dusk — a chestnut with a long flaxen-copper mane, head lowered and turned inward, resting against the shoulder of a dark dapple-grey with black feathered legs. Ankle-deep still water mirrors them almost perfectly. Golden-hour side light, pale peach and dove-grey sky, bare winter trees and a red-roofed barn far in the background with small grazing horses. Extremely slow, quiet motion”MiniMax H3, 图生视频, 5 秒, 有声, 40 积分, 输入图也是在 GPT Image 2.5 上生成的
“Pull focus to the people in the background and add more steam to the ramen bowl.”MiniMax H3, 图生视频, 10 秒, 有声, 260 积分, 输入图也是在 GPT Image 2.5 上生成的
用 MiniMax H3 能做什么
每个用途都附上我们会用的设置和提示词，以及要花多少。可以直接用，也可以改。
先说一句台词，再起大火
H3 Max Turbo，768p：摊主把台词一字不差地说完，然后炒锅里蹿起一大团火。提示词来自 Krea 的字节跳动 Seedance 2.5 对比海螺 H3 测试，那次 H3 Max 拍的是整个摊位，最后只有一小团火；Krea 生成的是 8 秒，这条是 10 秒。阿里通义万相 Wan 3.0 的页面也用了同一个提示词。
文生视频
768p
10 秒
有声
16:9
“Medium close-up, 50mm. A night-market noodle vendor in a white apron stands behind a steaming wok under bare hanging bulbs. He looks into the camera and says: "Thirty years. Same pan, same recipe." Then he tosses the noodles high and flames jump up from the wok. Camera: gentle living handheld that barely breathes, slight push-in. Audio: his voice, sizzling oil, crowd chatter, distant scooters. Photorealistic, warm practical light.”
她看着镜头，把台词原样说出来，周围是厨房的声音。提示词是公开发布的 H3 Max 示例；这条用的是更便宜的 H3 Max Turbo。
文生视频
768p
5 秒
有声
16:9
“A chef in her forties looks straight into the camera in a bright open kitchen and says, "The secret is you never crowd the pan." She smiles and turns back to the stove. Clean daylight from a window, white tile, flour on her apron, a strand of hair loose. Medium close-up, 50mm, slight handheld. Sound: her voice close and clear, a gentle sizzle, a knife on a board off screen.”
建议：台词放在引号里，写清楚谁说、怎么说：“looks straight into the camera … and says, “…””。
40 积分
定格黏土动画
黏土质感和一顿一顿的定格动作从头到尾都保持住了。大约第 4 秒，它自己切了一个特写，这是短提示词被改写后可能出现的情况。提示词是公开发布的 H3 Max 示例。
文生视频
768p
5 秒
有声
16:9
“Stop-motion claymation: a round green frog in a knitted scarf carries a stack of pancakes across a tiny kitchen set, sets it down, then looks at camera and blinks. Visible fingerprints in the clay, felt walls, warm practical lamps, stepped 12fps motion. Sound: playful pizzicato strings, soft clay squeaks, a plate clink.”
建议：不想要切镜头，就加一句“one continuous shot”。
40 积分
产品微距镜头
浓缩咖啡从冲煮手柄流下来，杯里的油脂慢慢铺开，全程是近距离微距。提示词是公开发布的 H3 Max 示例。
文生视频
768p
5 秒
有声
16:9
“Macro shot of espresso pulling from a chrome portafilter into a warm glass, thick golden crema blooming and swirling. Bright morning light through a cafe window, steam curling, water spots on the chrome, a few coffee grounds on the tray. 100mm macro, shallow focus, slight handheld drift. Sound: grinder winding down, the hiss of the pump, liquid pattering into glass, cafe chatter behind.”
建议：写清楚材质和打在上面的光（“thick golden crema”“chrome”），微距镜头里最显眼的就是这些。
“Two heavy draft horses stand together in a shallow flooded pasture at dusk — a chestnut with a long flaxen-copper mane, head lowered and turned inward, resting against the shoulder of a dark dapple-grey with black feathered legs. Ankle-deep still water mirrors them almost perfectly. Golden-hour side light, pale peach and dove-grey sky, bare winter trees and a red-roofed barn far in the background with small grazing horses. Extremely slow, quiet motion”
