Muse 免费做视频

Create a 10-second horizontal 16:9 video in Studio Ghibli-inspired hand-drawn animation style.
A young woman in a small countryside kitchen on a rainy afternoon stirs a pot of soup on an old stove; rain runs down the window, a cat sleeps on the windowsill, steam drifts up.
Gentle camera, soft warm colors, detailed painted background.
NARRATION (soft female voice, slow Mandarin Chinese, voice-over): "下雨天，就适合慢慢煮一锅汤。"
Audio: the narration, rain, bubbling soup, a quiet original piano melody. No subtitles, no on-screen text, no watermark.

Create a 10-second horizontal 16:9 explainer animation in simple stick-figure style: black line-drawn stick figures on a plain white background, minimal flat colors, clean and funny.
A stick figure runs on a hamster wheel while coins fall out of a hole in his pocket; he stops, looks at his empty wallet and scratches his head with a question mark above him.
NARRATION (calm, slightly humorous male voice, Mandarin Chinese, voice-over): "为什么你越忙，越存不下钱？"
Audio: the narration and light cartoon sound effects. No written words or numbers on screen, no subtitles, no watermark.

Create a 10-second horizontal 16:9 video in Chinese ink-wash painting style that comes alive: flowing brush strokes, rice-paper texture, black ink with light touches of color.
A Song dynasty scholar in a long robe stands alone at the bow of a small boat on a wide river at night, under a full moon, cliffs rising on both sides; his sleeves move in the wind.
NARRATION (deep, calm male voice, Mandarin Chinese, voice-over): "公元一零八零年，苏轼被贬到了黄州。"
Audio: the narration, water, wind, a soft guqin melody. No on-screen text, no seals, no subtitles, no watermark.

Create a 10-second vertical 9:16 first-person POV video, photorealistic.
You wake up in a wooden bed in Tang dynasty Chang'an. Your own hands push open a carved wooden window: below is a busy morning street with merchants, camels, lanterns and steaming food stalls. A servant in the doorway bows to you.
The camera is your eyes: natural head movement, your hands and silk sleeves visible in the frame.
VOICE (your own inner voice, confused young male, Mandarin Chinese): "这里……是长安？"
Audio: the inner voice, street noise, distant bells. No music, no on-screen text, no watermark.

Create a 10-second vertical 9:16 photorealistic video.
A chubby orange tabby cat wearing a tiny chef's hat and apron stands on its hind legs at a kitchen counter, tosses fried rice in a small wok with its paws, then turns to the camera proudly.
Handheld phone-video look, warm kitchen light.
VOICE (cute, slightly smug cartoon voice, Mandarin Chinese, the cat is speaking): "今天给主人做个蛋炒饭，喵。"
Audio: the cat's voice, sizzling wok. No music, no on-screen text, no watermark.

Create a 10-second horizontal 16:9 video in the style of a modern 3D animated family film: soft lighting, rounded cute character design, rich detail.
A small round robot with big glowing eyes steps out of a workshop door and sees snow for the first time; a snowflake lands on its hand, its eyes widen, and it spins around happily.
NARRATION (warm female storyteller voice, Mandarin Chinese, voice-over): "小机器人第一次见到了雪。"
Audio: the narration, soft wind, gentle original music box melody. No on-screen text, no watermark.

Create a 10-second horizontal 16:9 video in the style of a high-end nature documentary, photorealistic, cinematic.
Late Cretaceous: a herd of triceratops drinks at a river at dusk. In the sky, a bright streak appears and grows; the dinosaurs lift their heads toward it.
Slow, steady camera.
NARRATION (deep, serious male documentary voice, Mandarin Chinese, voice-over): "六千六百万年前，一颗小行星改变了一切。"
Audio: the narration, river, low dinosaur calls, a low orchestral drone. No on-screen text, no watermark.

Create a 10-second vertical 9:16 video, photorealistic with a cartoon twist.
Inside an open fridge, a carton of milk with a small animated face and tiny arms sits at the back of the shelf, looking grumpy. It sighs, looks at the camera and complains. A tomato next to it rolls its eyes.
VOICE (tired, sarcastic middle-aged male voice, Mandarin Chinese, the milk carton is speaking with lip sync): "我已经在这里躺了三个星期了。"
Audio: the voice and fridge hum. No music, no readable text on any package, no watermark.

Create a 10-second vertical 9:16 photorealistic video.
A friendly 40-year-old Chinese woman in a light blue shirt stands in a bright home kitchen, holding a bowl of leftover rice, and talks directly to the camera like a short-video host.
Tripod shot, medium close-up, natural daylight.
DIALOGUE (clear, friendly female voice, standard Mandarin Chinese, spoken on camera with accurate lip sync): "隔夜饭到底能不能吃？今天一次讲清楚。"
Audio: her voice and quiet room sound only. No music, no subtitles, no on-screen text, no watermark.

Create a 10-second vertical 9:16 video in Chinese animation (donghua) style: detailed 2D character art, dramatic lighting.
Night, a courtyard in the rain. A woman in a red robe holds a paper umbrella and faces a man in black armor standing at the gate. Close-up on her face, then his.
DIALOGUE (Mandarin Chinese, two different voices, with lip sync):
00:02 SHE, cold and steady: "三年了，你终于肯回来了。"
00:06 HE, low and tired: "我回来，是为了带你走。"
Audio: the two voices, rain, a tense string note. No subtitles, no on-screen text, no watermark.

Create a 10-second horizontal 16:9 video that looks like real home-video footage from 1995 in a southern Chinese city: soft VHS texture, faded colors, slight tracking noise, 4:3 picture inside the frame.
Summer evening on an old street: adults sit on bamboo chairs outside their doors fanning themselves, a man rides past on a bicycle with a block of ice on the back, a small shop has a freezer by the door, an old TV glows inside.
Handheld camcorder feel.
NARRATION (warm, nostalgic middle-aged male voice, Mandarin Chinese, voice-over): "那时候的夏天，是从一根冰棍开始的。"
Audio: the narration, cicadas, bicycle bell, distant TV sound. No on-screen text, no date stamp, no watermark.

Create a 10-second vertical 9:16 photorealistic video. The camera is her boyfriend's phone; she talks to the lens.
A 26-year-old adult Chinese woman with shoulder-length wavy black hair, light natural makeup, cream cardigan, sits across a café table by the window. She pushes a slice of cake toward the camera, then rests her chin on her hand.
Real handheld phone footage, soft daylight.
DIALOGUE (soft, bright young female voice, playful Mandarin Chinese, spoken on camera with accurate lip sync): "你尝一口，这个真的很好吃。"
Audio: her voice and quiet café ambience. No music, no subtitles, no on-screen text, no watermark.

Create a 10-second vertical 9:16 video, 1080p.
A 26-year-old adult Chinese woman with shoulder-length wavy black hair sits across a café table from the camera on a sunny afternoon. She pushes a slice of cake toward the camera, looks into the lens and speaks.
VOICE: a soft, bright young female voice, natural conversational Mandarin Chinese, not a broadcast voice.
DIALOGUE (spoken on camera, accurate lip sync): "你尝一口，这个真的很好吃。"
It should look like a real phone video: natural handheld shake, soft daylight.
Audio: her voice and quiet café ambience. No music, no subtitles, no on-screen text, no watermark.

Generate 5 separate photorealistic images of the same person. Keep her face identical in all of them.

PERSON: "Xiao Man", a 26-year-old adult Chinese woman, shoulder-length black hair with soft natural waves, oval face, light natural makeup, realistic skin texture, a small mole under her left eye, slim build. White fitted short-sleeve T-shirt, light blue straight-leg jeans, white sneakers, a small brown shoulder bag, a thin silver necklace.

Image 1: front view, head and shoulders, relaxed smile, plain light gray background, soft even light.
Image 2: three-quarter view, half body, looking slightly off camera, plain light gray background.
Image 3: full body, standing on a quiet tree-lined city street in the afternoon, candid.
Image 4: close-up of her face laughing, natural window light.
Image 5: close-up of her face mid-sentence, mouth slightly open as if talking to someone behind the camera.

Use the 5 images you just made as the reference for Xiao Man's appearance. They are appearance references only — do not use any of them as the first frame.

Create a 30-second vertical 9:16 1080p video. The camera is her boyfriend's phone; she talks to him (to the lens) the whole time.

PERSON: "Xiao Man", a 26-year-old adult Chinese woman, shoulder-length black hair with soft natural waves, oval face, light natural makeup, realistic skin texture, a small mole under her left eye, slim build. White fitted short-sleeve T-shirt, light blue straight-leg jeans, white sneakers, a small brown shoulder bag, a thin silver necklace. Keep her face, hair, outfit and accessories identical in every shot.
VOICE: a soft, bright young female voice, natural conversational Mandarin Chinese, playful and warm, not a broadcast voice. Keep the same voice in every line.

PLACE: a quiet older neighborhood in a Chinese city — narrow street, plane trees, small shops, parked bicycles, a small convenience store. No landmarks, no brands, no readable signs.
STYLE: real handheld phone footage — natural shake, imperfect framing, slight noise. Not a commercial, no gimbal, no slow motion, no beauty filter.

STORY AND DIALOGUE (all lines spoken on camera in Mandarin, accurate lip sync):
00:00–00:05 She walks out of an apartment gate, sees the camera and smiles. She says: "你怎么才来呀，我等你好久了。"
00:05–00:10 She comes out of the convenience store with a cold drink and presses the bottle to the camera. She says: "给你买的，快拿着，冰的。"
00:10–00:15 They walk down a quiet street; she walks backward facing the camera. She says: "今天你说去哪，我就去哪。"
00:15–00:20 She sits on a low wall under the trees and picks a leaf out of her hair, laughing. She says: "不许拍，丑死了。"
00:20–00:25 She stands up and holds out her hand toward the camera. She says: "走啦，带你去吃好吃的。"
00:25–00:30 She turns and walks ahead, then looks back over her shoulder. She says: "快点跟上！" Hold one second, cut to black.

AUDIO: her voice plus natural street sound — footsteps, distant traffic, cicadas, leaves. No music, no voice-over, no subtitles.

No identity drift, no outfit change, no extra fingers, no duplicate people, no CGI look. No on-screen text, logos or watermark.

The 3 attached images show the same woman, Xiao Man. Use them as appearance references only.

Create a 10-second vertical 9:16 1080p video. The camera is her boyfriend's phone; she talks to the lens.

PERSON: "Xiao Man", a 26-year-old adult Chinese woman, shoulder-length black hair with soft natural waves, oval face, light natural makeup, realistic skin texture, a small mole under her left eye, slim build. Keep her face and hair identical to the attached images.
VOICE: a soft, bright young female voice, natural conversational Mandarin Chinese, playful and warm, not a broadcast voice.
OUTFIT: cream knit cardigan over a white top, light jeans.

SCENE: She sits across a café table by the window. She pushes a slice of cake toward the camera, then rests her chin on her hand and watches.
DIALOGUE (spoken on camera in Mandarin, accurate lip sync):
00:01 "你尝一口，这个真的很好吃。"
00:06 "怎么样？我没骗你吧。"

Real handheld phone footage, soft daylight, natural shake.
Audio: her voice and quiet café ambience. No music, no subtitles, no on-screen text, no watermark.

Same woman, same face, same voice, same real-phone-footage style. Make another 10-second vertical video.
OUTFIT: beige trench coat, white T-shirt, jeans.
SCENE: She walks ahead across a pedestrian bridge at dusk with city lights behind her, then turns around to face the camera, hair blowing in the wind.
DIALOGUE (spoken on camera in Mandarin, accurate lip sync):
00:01 "走快点啦，日落要没了。"
00:06 "帮我拍一张，要拍好看一点哦。"
Audio: her voice, wind and city ambience. No music.

Same woman, same face, same voice, same real-phone-footage style. Make another 10-second vertical video.
OUTFIT: sports tank top, leggings, hair in a ponytail.
SCENE: In a gym, she finishes a set of dumbbell curls, puts the weights down, wipes her forehead with a towel and grins at the camera, out of breath.
DIALOGUE (spoken on camera in Mandarin, slightly out of breath, accurate lip sync):
00:01 "最后一组，你帮我数。"
00:07 "呼……今天晚上你请客。"
Audio: her voice and gym ambience. No music.

The 3 attached images show the same woman, Xiao Man. Use them as appearance references only.

Create a 10-second vertical 9:16 1080p video. The camera is her boyfriend's phone; she talks to the lens.

PERSON: "Xiao Man", a 26-year-old adult Chinese woman, shoulder-length black hair with soft natural waves, oval face, light natural makeup, realistic skin texture, a small mole under her left eye, slim build. Keep her face and hair identical to the attached images.
VOICE: a soft, bright young female voice, natural conversational Mandarin Chinese, playful and warm, not a broadcast voice.
OUTFIT: light yellow sundress, straw hat in her hand.

SCENE: She walks barefoot along the edge of the waves on a beach at sunset, kicks a little water toward the camera and laughs.
DIALOGUE (spoken on camera in Mandarin, accurate lip sync):
00:01 "水好凉！你也下来嘛。"
00:06 "不许拍我丑照，听到没有。"

Real handheld phone footage, warm sunset light, natural shake.
Audio: her voice, waves and wind. No music, no subtitles, no on-screen text, no watermark.

OUTFIT: oversized white shirt, black shorts, white sneakers.

SCENE: In a dance studio with a mirror wall, she points at the camera, does a short simple pop dance routine, finishes with a pose and bursts out laughing.
DIALOGUE (spoken on camera in Mandarin, accurate lip sync):
00:00 "我新学的，你看好了。"
00:07 "怎么样，是不是很厉害？"

Audio: her voice, an original upbeat pop beat during the dance, studio ambience. No subtitles, no on-screen text, no watermark.

The 3 attached images show the same woman, Xiao Man. Use them as appearance references only.

Create a 10-second vertical 9:16 1080p video.

PERSON: "Xiao Man", a 26-year-old adult Chinese woman, shoulder-length black hair with soft natural waves, oval face, light natural makeup, a small mole under her left eye, slim build. Oversized gray sweater.
SCENE: A quiet morning at home. She pours coffee, carries the cup to the window seat, pulls a blanket over her knees and looks outside. She does not speak on camera.
VOICE-OVER (her inner voice, soft and slow Mandarin Chinese, no lip movement): "周末不想出门的时候，我就给自己煮一杯咖啡，坐在窗边发呆。"
Audio: the voice-over, soft room sound, a gentle original piano melody at low volume. No subtitles, no on-screen text, no watermark.

Same woman, same face. Make another 10-second vertical video.
OUTFIT: white T-shirt, light jeans.
SCENE: She sits on a sofa at home scrolling her phone, then looks up at the camera.
DIALOGUE (Mandarin Chinese; two different voices):
00:01 MALE VOICE, off-screen, behind the camera, calm and low: "晚上想吃什么？"
00:03 SHE, on camera, bright: "火锅！"
00:05 MALE VOICE, off-screen, amused: "又是火锅？"
00:07 SHE, on camera, laughing: "就要火锅。"
Audio: the two voices and quiet room sound only. No music, no subtitles.

Same woman, same face. Make another 10-second vertical video: selfie-style shot on a sunny street, she looks into the lens and says, in Mandarin Chinese with a soft Taiwanese accent: "今天天气也太好了吧，我们出去走走好不好？" Accurate lip sync. Audio: her voice and street ambience only.

Same shot again, but she says the line in Cantonese: "今日天氣咁好，不如出去行下啦？" Accurate lip sync.

Same shot again, but she says the line in English: "The weather is so nice today. Let's go for a walk, okay?" Accurate lip sync.

Same style, same character, same voice. Make another 10-second video.
SCENE: [新一集的画面]
NARRATION / DIALOGUE (Mandarin Chinese): "[新一集的台词，20 个字以内]"

Same stick-figure style, same narrator voice. Make another 10-second video.
SCENE: The stick figure gets his salary — a bag of coins drops into his hands — then five other stick figures each grab a handful and walk away, leaving him with one coin.
NARRATION (Mandarin Chinese): "工资一到手，先被五件事分走了。"

Same stick-figure style, same narrator voice. Make another 10-second video.
SCENE: The stick figure puts one coin into a jar first, then pays the others; the jar slowly fills up and he smiles.
NARRATION (Mandarin Chinese): "换个顺序，先存再花，结果完全不一样。"

Same animation style, same young woman, same narrator voice. Make another 10-second video.
SCENE: Early morning, she opens the wooden shutters of the same kitchen, sunlight pours in, she puts a kettle on the stove and the cat stretches on the windowsill.
NARRATION (Mandarin Chinese): "天晴了，先烧一壶水。"

Same animation style, same young woman, same narrator voice. Make another 10-second video.
SCENE: Evening, she carries a tray with two bowls of noodles to a small table by the window; the cat jumps onto the other chair; fireflies outside.
NARRATION (Mandarin Chinese): "今天的晚饭，有人陪。"

Same ink-wash style, same scholar, same narrator voice. Make another 10-second video.
SCENE: The scholar, now in plain farmer's clothes, hoes a small vegetable field on a hillside, wipes his sweat and laughs at the sky.
NARRATION (Mandarin Chinese): "没有俸禄，他就自己开了一块荒地。"

Same ink-wash style, same scholar, same narrator voice. Make another 10-second video.
SCENE: Night, he sits by a small lamp writing with a brush; the characters lift off the paper as ink and drift out the window toward the moon.
NARRATION (Mandarin Chinese): "也正是在这里，他写下了一生最好的文字。"

I want to start a short-video account using only videos you generate. Suggest 3 content niches you can produce reliably and consistently, and explain why for each.
Then make a 10-second sample video with Mandarin Chinese narration for the niche you think is best.
Before generating, show me the plan and estimate how much of my weekly allowance it will use. Wait for my OK.

Keep the video picture exactly as it is. Replace only the audio:
1. Generate the narration as a separate voice track that says the full sentence: "[把这里换成你要它说的那句话]"
2. Place it starting at 00:02 and mix it with the ambient sound.
3. Before you send me the file, transcribe the final audio yourself and check it against the sentence above, character by character. If any character is missing or wrong, fix it and check again.
Send me the new video and tell me what your transcription check found.

保持视频画面完全不变，只替换音频：先把原片里的旁白转写出来，告诉我原片实际说了什么、从第几秒开始、漏了哪些字；然后去掉原来的人声，单独生成一条[温暖的女声 / 沉稳的男声]旁白，完整说出「[把这里换成你要它说的那句话]」，从第 2 秒开始，和环境音、音乐混在一起。发给我之前，请你自己把成片音频转写一遍，和这句话逐字核对，缺字或错字就修到对为止，最后用中文告诉我核对结果。

请帮我修「白垩纪三角龙与小行星」那条 10 秒纪录片视频的旁白（文件在你的 imagine_media 目录里，就是另一个旁聊里那条三角龙在河边喝水的片子）。要求：全程只用你电脑里已经有的工具和已经缓存的模型（就是今天修机器人、苏轼那两条时用过的那套），不要发起任何新的联网下载；如果不联网就做不了，请直接停下来告诉我缺什么。步骤：先把原片旁白转写出来，告诉我原片实际说了什么、从第几秒开始；然后画面保持不变，去掉原来的人声，单独生成一条沉稳的男声旁白，完整说出「六千六百万年前，一颗小行星改变了一切。」，从第 2 秒开始；发给我之前自己把成片音频转写一遍逐字核对，并确认原来的人声没有残留。用中文告诉我结果。

这是一次盲听检查。请不要查看其他对话里的任何台词或目标句，也不要猜原本想让它说什么，只报你实际听到的。只用电脑里已有的工具和已经缓存的听写模型，不要发起任何新的联网或下载；做不了就停下来告诉我缺什么。请在主目录里找出[这几条视频]的最终成片。对每个文件：1）给出文件名、时长、分辨率；2）把整条音轨从 0 秒到结尾完整转写，不要只转其中一段，用 tiny、base、small、medium 四个模型各转一次，原样贴出每次的转写文本和每一段人声的起止时间；3）说明整条音轨里一共检测到几段人声。不要评价对错，不要和任何目标句比较。用中文回答，不生成新视频，不修改任何文件。

这是我自己频道的视频：https://www.youtube.com/watch?v=fyag4UafiEc 。请把它的字幕完整拉下来，然后做三件事：1）按内容分成章节，每章给出起始时间和一句话摘要；2）挑出 5 句最适合剪成短视频的金句，标出时间点；3）告诉我你是用什么方法拿到字幕的，中间有没有遇到拦截。用中文回答。

帮我做一张对比表并导出成 Excel 文件：对比 Muse、ChatGPT dots、Grok Bot 三个产品。列：所属公司、发布日期、免费额度、付费档位与价格、开放地区、云端电脑配置（官方有没有公布）、能连接的主要应用。每一格都要附来源链接；官方没有公布或你查不到的写「未公布」，不要推测。做完把 Excel 文件发给我，并用三句话总结最大的区别。用中文回答。

用你的云端电脑帮我做一个单页网站：标题「Fanko AI範式」；一段介绍：熱門的 AI 產品和工具，我親手用過一遍，再告訴你它到底能不能用、適合誰、坑在哪裡；放我 YouTube 频道（https://www.youtube.com/@FankoAIPractice）最新 3 期视频的标题、封面和链接；页面要适配手机。做完之后：1）给我一个可以在浏览器里打开的访问地址；2）告诉我这个地址是不是任何人都能打开、能保留多久、什么情况下会失效；3）把网页源文件也发给我一份。页面里不要放任何邮箱、电话等个人信息。用中文回答。

帮我做一份今天的 AI 简报样例（只做这一次，先不要设成定时任务）：1）过去 24 小时 X 上关于 Muse、dots、Grok Bot 的帖子，各挑 3 条互动最高的，附链接和一句话摘要；2）过去 24 小时 YouTube 上这三个产品的中文新视频，挑播放最高的 5 条，附链接和播放量；3）最后用三句话告诉我：今天有没有值得做一期视频的新东西。查不到或者不确定的内容请标「未确认」，不要编。做完后告诉我：如果要每天早上 8 点自动发一份，该怎么设置、每次大概花多少额度。

请用你的云端电脑实际查一下再回答，不要凭印象：1）这台电脑的 CPU 核数、内存、硬盘大小和已用空间、操作系统；2）有没有显卡；3）这台电脑会保留多久，什么情况下会被重置，我存在里面的文件会不会丢；4）我这周的额度已经用了百分之多少、什么时候重置。每一项请说明是实际查到的还是你的推测，用中文回答。

再帮我实际查两件事，查不到就直说查不到、不要估：1）这一周（从上次额度重置到现在）我一共让你生成了多少条视频、多少张图片，请去你的文件目录或资源库里数一下；2）现在周额度用到百分之多少了（刚才是 71%）。用中文回答。