APIMODELSAPIMODELS

22+ Muse Video Chinese Period & Historical Prompts

22+ prompts. More than 200 Muse Video prompts that creators posted on X after running them in Meta's Muse, each credited to its creator and linked to the original post, with the clip it produced where the post has one. Short prompts, and those whose authors invited reuse, are quoted in full; longer ones are excerpted, and the full text is one click away in the original post.

← All 204 Muse Video prompts

Last updated: · Muse Video API — pricing & playground · API docs

TL;DR

Muse Video is the video model in Meta's Muse AI family. Most prompts on this page were run inside Meta's Muse app, a chat agent that accepts very long prompts and plain instructions such as "turn the images in this post into a video". Through apimodels.app the same model is available as muse-video: text, one first frame or up to four reference images in; a 720p clip of 4 to 20 seconds out, 16:9 or 9:16; prompts up to 4,000 characters; $0.037 per requested second, failed tasks not charged, and not every request succeeds. The prompts are grouped by use: reference-sheet multi-shot cuts, boyfriend POV, selfie and vlog, dance, period pieces, fantasy and CG, long multi-clip scripts and one-liners.

Hover to preview · click for sound

Sword dance in white on a bamboo-forest terrace

Excerpt

古风武侠电影质感,一位年轻东方女子身着月白色广袖交领长裙,外披轻薄青色纱衣,黑色长发半束高髻,银色发簪与细长发带随风飘动,手持三尺青锋长剑,站在晨雾缭绕的竹林石台中央。她神情清冷专注,身姿挺拔轻盈。 起势时女子静立半息,右手执剑自然垂落,左手剑指缓缓抬起;随后脚尖轻点石台,身体向前滑步,长剑由下向上划出一道流畅弧线,衣袖与裙摆延迟半拍跟随身体旋转。接连续舞剑动作:转腕挽剑花、侧身横斩、低身回旋、反手挑剑、踏步刺剑,动作连贯且具有真实武术重心变化,手腕、肩部、腰胯、脚步形成完整动力链。中段突然加速,她旋身一周半,长发与纱衣形成明显离心运动,剑锋掠过镜头前景,随后腾空轻跃,空中收腿转体,落地瞬间屈膝卸力,再顺势完成一记由低至高的斜挑剑。 镜头从中远景开始,低机位缓慢 dolly-in 推近,随后使用 stabilized tracking shot 沿人物侧前方弧形跟拍;旋转舞剑时镜头同步进行半环绕 orbit,保持人物面部与剑身始终清晰;腾空瞬间轻微升格 slow motion,镜头由低向上 tilt,落地后迅速恢复正常速度, …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
806 characters in the original post
by @RealHanyaHuSource
Hover to preview · click for sound

East Tower of Xianyang, ink-wash poem in 5 parts

Excerpt

# DAY079《咸阳城东楼》Omni 纯文生视频提示词 ## 统一生成设置 - 模式:纯文生视频(Text to Video),不上传参考图片、参考视频、配音或任何音频。 - 共5段,每段10秒,9:16竖屏,建议1080×1920。 - 输出纯画面、无声;人物不说话、不做朗读口型。 - 统一美术:唐代咸阳深秋古风水墨设色动画,宣纸肌理,墨青、灰蓝、芦苇枯黄、夕照暗金为主,古城楼、渭水、秦汉旧苑遗迹,电影感大景别,缓慢稳定运镜。 - 人物连续性:许浑为四十岁左右唐代文士,清瘦自然面容,深色束发,灰青或灰褐长袍,登临怀古的沉静气质;不做华丽官服。 - 最高优先级:全程完全无文字。禁止字幕、诗句、标题、作者名、书法、印章、城楼牌匾、宫苑匾额、碑刻、文书、旗帜文字、水印、Logo、UI、英文、数字、伪汉字和乱码。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
1547 characters in the original post
by @7998l201Source
Hover to preview · click for sound

Bring in the Wine: a Tang banquet in 45 seconds

生成一段唐诗的写实电影视频,45秒,内容是李白的《将进酒》节选,要还原唐朝的宴会场景,要有多景别,运动运镜,要体现李白的豪放和宴会的开心氛围,16:9

by @PixelAigcSource

Two swordswomen: from the dragon palace to the heavenly palace

Excerpt

仙侠双姝竞速飞行的两段完整提示词,生成时用的就是这两版: 写实取向的古装仙侠高速穿行,一镜到底,中间不切镜。两名主角均为年轻成年女子,黑色长发,身形高挑纤细,以背面和后侧面为主,不展示正脸特写,不回头摆拍。白衣女子穿象牙白宽袖古装长衣、层叠浅色下摆,长发部分束起带浅色发饰,右手始终握一柄细长直剑(只是手持道具,不御剑不施法);青衣女子穿青绿色宽袖古装外衣、浅色内衬和束腰,长发半束后自然垂落。两人服装体型发型全程一致。 两人是竞速较劲关系,不是编队飞行:不断互相追赶反超,每次反超都要完整呈现——后方追近到半个身位、侧向错开、从左侧或右侧掠过、拉开距离,不许瞬移。 剧情(A段:起飞→穿瀑→入水→海底龙宫): 0-1.5秒:开场已在动作中,紧贴青衣女子背后,白衣在左前方,两人在依崖而建的狭窄木廊上快速助跑两三步,木柱横梁岩壁从近处掠过,右侧是云雾深谷;两人同时从木廊尽头蹬地跃出,转为前倾飞行姿态,双腿收向身后,此后双脚不再触碰任何东西。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
9 timed beats · 2507 characters in the original post
Watch on X
by @7998l201Source
Hover to preview · click for sound

Two swordswomen: cliffs and eaves

Excerpt

写实取向的古装仙侠高速穿行,一镜到底,中间不切镜。两名主角均为年轻成年女子,黑色长发,身形高挑纤细,以背面和后侧面为主,不展示正脸特写,不回头摆拍。白衣女子穿象牙白宽袖古装长衣、层叠浅色下摆,长发部分束起带浅色发饰,右手始终握一柄细长直剑(只是手持道具,不御剑不施法);青衣女子穿青绿色宽袖古装外衣、浅色内衬和束腰,长发半束后自然垂落。两人服装体型发型全程一致。 两人是竞速较劲关系,不是编队飞行:不断互相追赶反超,每次反超都要完整呈现——后方追近到半个身位、侧向错开、从左侧或右侧掠过、拉开距离,不许瞬移。 剧情: 0-1.5秒:开场已在动作之中,两人沿着悬崖峭壁上依崖而建的楼阁檐口高速横向移动,脚尖轮流点过翘起的檐角借力,身体向岩壁一侧微倾,摄影机在后方数个身位追赶,檐角从画面两侧高速擦过,下方是云雾翻腾的深渊。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
5 timed beats · 1134 characters in the original post
by @7998l201Source
Hover to preview · click for sound

Two swordswomen: golden sea of clouds

Excerpt

写实取向的古装仙侠高速穿行,一镜到底,中间不切镜,整体基调金碧辉煌、唯美壮丽。两名主角均为年轻成年女子,黑色长发,身形高挑纤细,以背面和后侧面为主,不展示正脸特写,不回头摆拍。白衣女子穿象牙白宽袖古装长衣、层叠浅色下摆,长发部分束起带浅色发饰,右手始终握一柄细长直剑(只是手持道具,不御剑不施法);青衣女子穿青绿色宽袖古装外衣、浅色内衬和束腰,长发半束后自然垂落。两人服装体型发型全程一致。 两人是竞速较劲关系,不是编队飞行:不断互相追赶反超,每次反超都要完整呈现——后方追近到半个身位、侧向错开、从左侧或右侧掠过、拉开距离,不许瞬移。 剧情: 0-1.5秒:开场已在动作之中,黎明时分,两人高速掠过一片金色云海,云层如熔金般翻涌,一轮红日正在地平线上升起;金光洒在两人身上,衣摆镶上金边;摄影机在后方数个身位追赶。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
5 timed beats · 965 characters in the original post
by @7998l201Source

Two swordswomen: ice crevasse in the snow mountains

Excerpt

写实取向的古装仙侠高速穿行,一镜到底,中间不切镜。两名主角均为年轻成年女子,黑色长发,身形高挑纤细,以背面和后侧面为主,不展示正脸特写,不回头摆拍。白衣女子穿象牙白宽袖古装长衣、层叠浅色下摆,长发部分束起带浅色发饰,右手始终握一柄细长直剑(只是手持道具,不御剑不施法);青衣女子穿青绿色宽袖古装外衣、浅色内衬和束腰,长发半束后自然垂落。两人服装体型发型全程一致。 两人是竞速较劲关系,不是编队飞行:不断互相追赶反超,每次反超都要完整呈现——后方追近到半个身位、侧向错开、从左侧或右侧掠过、拉开距离,不许瞬移。 剧情: 0-1.5秒:开场已在动作之中,两人贴着雪山山脊高速向前,脚下是万丈冰崖,远处雪峰林立,云海在下方翻涌;寒风凛冽,衣摆翻卷;摄影机在后方数个身位追赶。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
5 timed beats · 958 characters in the original post
Watch on X
by @7998l201Source

Two swordswomen: bamboo sea and water town

Excerpt

写实取向的古装仙侠高速穿行,一镜到底,中间不切镜。两名主角均为年轻成年女子,黑色长发,身形高挑纤细,以背面和后侧面为主,不展示正脸特写,不回头摆拍。白衣女子穿象牙白宽袖古装长衣、层叠浅色下摆,长发部分束起带浅色发饰,右手始终握一柄细长直剑(只是手持道具,不御剑不施法);青衣女子穿青绿色宽袖古装外衣、浅色内衬和束腰,长发半束后自然垂落。两人服装体型发型全程一致。 两人是竞速较劲关系,不是编队飞行:不断互相追赶反超,每次反超都要完整呈现——后方追近到半个身位、侧向错开、从左侧或右侧掠过、拉开距离,不许瞬移。 剧情: 0-1.5秒:开场已在动作之中,两人低空掠过一片无边竹海,竹梢在脚下如波浪般起伏,竹叶被气流带起漫天飞舞;摄影机在后方数个身位追赶。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
10 timed beats · 1946 characters in the original post
Watch on X
by @7998l201Source
Hover to preview · click for sound

Two swordswomen: Lantern Festival

Excerpt

写实取向的古装仙侠高速穿行,一镜到底,中间不切镜,整体基调灯火璀璨、唯美浪漫。两名主角均为年轻成年女子,黑色长发,身形高挑纤细,以背面和后侧面为主,不展示正脸特写,不回头摆拍。白衣女子穿象牙白宽袖古装长衣、层叠浅色下摆,长发部分束起带浅色发饰,右手始终握一柄细长直剑(只是手持道具,不御剑不施法);青衣女子穿青绿色宽袖古装外衣、浅色内衬和束腰,长发半束后自然垂落。两人服装体型发型全程一致。 两人是竞速较劲关系,不是编队飞行:不断互相追赶反超,每次反超都要完整呈现——后方追近到半个身位、侧向错开、从左侧或右侧掠过、拉开距离,不许瞬移。 剧情: 0-1.5秒:开场已在动作之中,上元之夜,两人低空掠过一座古城,城中万盏花灯如星河落地,街道上灯火蜿蜒;雪花轻轻飘落,灯火在雪中晕开暖光;摄影机在后方数个身位追赶。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
5 timed beats · 962 characters in the original post
by @7998l201Source
Hover to preview · click for sound

Two swordswomen: osmanthus grove by moonlight

Excerpt

写实取向的古装仙侠高速穿行,一镜到底,中间不切镜,整体基调清冷皎洁、梦幻绝美。两名主角均为年轻成年女子,黑色长发,身形高挑纤细,以背面和后侧面为主,不展示正脸特写,不回头摆拍。白衣女子穿象牙白宽袖古装长衣、层叠浅色下摆,长发部分束起带浅色发饰,右手始终握一柄细长直剑(只是手持道具,不御剑不施法);青衣女子穿青绿色宽袖古装外衣、浅色内衬和束腰,长发半束后自然垂落。两人服装体型发型全程一致。 两人是竞速较劲关系,不是编队飞行:不断互相追赶反超,每次反超都要完整呈现——后方追近到半个身位、侧向错开、从左侧或右侧掠过、拉开距离,不许瞬移。 剧情: 0-1.5秒:开场已在动作之中,月夜,两人高速掠过一片桂花林,金黄色的桂花如雨般飘落,空气中仿佛能闻到花香;一轮巨大的圆月悬在林梢,月光如水;摄影机在后方数个身位追赶。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
5 timed beats · 989 characters in the original post
by @7998l201Source
Hover to preview · click for sound

Costume romance: under summer-night lanterns

只参考两张人物角色图的脸部、发型、五官形象(图1=女主·林晚棠角色图,图2=男主·顾承砚角色图),人物身份、脸型、五官、发型、气质必须与角色图严格一致,锁定形象;身材、服装按本集提示词执行。生成一段10秒短视频。 【整体风格】国产古风甜宠影视剧质感。写实古风电影摄影,夏夜暖黄灯光,低饱和电影调色,细腻胶片颗粒,浅景深,真实皮肤与布料质感,温馨浪漫。 【人物设定】女主·林晚棠:淡绿襦裙,白里透红。男主·顾承砚:深蓝常服,阳光温柔。 【场景】夏夜庭院,萤火虫飞舞,灯笼微光,栏杆。 【10秒时间轴】0.0–3.0s:女主趴在栏杆上数萤火虫,神情专注可爱。3.0–6.5s:男主变出一盏纱灯,把捉来的萤火虫放进去,递给她。6.5–10.0s:女主捧着纱灯,眼睛比萤火虫还亮,惊喜地笑。定格在灯光萤火的温馨。 【硬性禁止项】脸部严格锁定角色图,禁换脸;萤火虫数量合理,禁凭空暴增;纱灯传递连贯,禁凭空消失;禁第三人;禁手指异常肢体变形;禁表情跳变;禁字幕水印UI;禁动漫感塑料皮过强HDR。

by @7998l201Source
Hover to preview · click for sound

Costume romance: the swing (episode 3)

只参考两张人物角色图的脸部、发型、五官形象(图1=女主·林晚棠角色图,图2=男主·顾承砚角色图),人物身份、脸型、五官、发型、气质必须与角色图严格一致,锁定形象;身材、服装按本集提示词执行。生成一段10秒短视频。 国产古风甜宠影视剧质感。写实古风电影摄影,暖白自然光,低饱和粉绿电影调色,细腻胶片颗粒,浅景深,真实皮肤与布料质感。男主阳光帅气、爱笑;女主白里透红、娇俏灵动。 女主·林晚棠:浅粉襦裙。男主·顾承砚:天青常服,阳光开朗。 春日庭院,桃花树下秋千,花瓣纷飞。 0.0–3.0s:女主坐秋千,男主在身后推,秋千越荡越高,裙摆飞扬,花瓣纷飞。3.0–6.5s:女主笑声洒满庭院,男主稳稳护着,喊抓紧。6.5–10.0s:女主回头,逆光中男主笑脸灿烂,比桃花还好看。定格在逆光相视的美好。 脸部严格锁定角色图,禁换脸;秋千摆动幅度合理,禁飞出秋千;禁第三人;禁手指异常肢体变形;禁表情跳变;禁字幕水印UI;禁动漫感塑料皮过强HDR。

by @7998l201Source
Hover to preview · click for sound

Costume romance: jealousy (episode 4)

只参考两张人物角色图的脸部、发型、五官形象(图1=女主·林晚棠角色图,图2=男主·顾承砚角色图),人物身份、脸型、五官、发型、气质必须与角色图严格一致,锁定形象;身材、服装按本集提示词执行。生成一段10秒短视频。 国产古风甜宠影视剧质感。写实古风电影摄影,午后暖白阳光,低饱和电影调色,细腻胶片颗粒,浅景深,真实皮肤与布料质感,轻松搞笑。男主阳光帅气、爱笑;女主白里透红、娇俏灵动。 女主·林晚棠:淡青襦裙,怀抱白猫汤圆。男主·顾承砚:月白常服,幼稚吃醋。 午后庭院,躺椅,白猫。 0.0–3.0s:女主抱着白猫,男主盯着猫酸溜溜:它每天抱你几个时辰?3.0–6.5s:女主:你连猫的醋都吃?男主把猫抱走放一边。6.5–10.0s:男主赖进女主怀里原来的位置:现在轮到我了。女主笑倒在他怀里,白猫在旁边舔爪。定格在欢乐。 脸部严格锁定角色图,禁换脸;白猫全程在场,禁凭空消失;禁第三人;禁手指异常肢体变形;禁表情跳变;禁字幕水印UI;禁动漫感塑料皮过强HDR。

by @7998l201Source
Hover to preview · click for sound

Costume romance: taking measurements (episode 5)

只参考两张人物角色图的脸部、发型、五官形象(图1=女主·林晚棠角色图,图2=男主·顾承砚角色图),人物身份、脸型、五官、发型、气质必须与角色图严格一致,锁定形象;身材、服装按本集提示词执行。生成一段10秒短视频。 国产古风甜宠影视剧质感。写实古风电影摄影,午后暖白阳光,低饱和电影调色,细腻胶片颗粒,浅景深,真实皮肤与布料质感,暧昧甜蜜。男主阳光帅气、爱笑;女主白里透红、娇俏灵动。 女主·林晚棠:浅绿襦裙。男主·顾承砚:天青常服。 午后绣房,布料、软尺,阳光透窗。 0.0–3.0s:绣房里,男主接过软尺,主动说我来,为女主量腰围。3.0–6.5s:男主俯身,软尺绕过女主腰间,呼吸拂过她耳畔,女主僵住不敢动。6.5–10.0s:两人耳尖都红了,男主量完发现数字一个没记住,女主笑出声。定格在暧昧的笑。 脸部严格锁定角色图,禁换脸;软尺使用连贯,禁凭空消失;禁第三清晰人物(裁缝虚化远景);禁手指异常肢体变形;禁表情跳变;亲密点到为止;禁字幕水印UI;禁动漫感塑料皮过强HDR。

by @7998l201Source
Hover to preview · click for sound

Costume romance: a stolen kiss (episode 6)

只参考两张人物角色图的脸部、发型、五官形象(图1=女主·林晚棠角色图,图2=男主·顾承砚角色图),人物身份、脸型、五官、发型、气质必须与角色图严格一致,锁定形象;身材、服装按本集提示词执行。生成一段10秒短视频。 国产古风甜宠影视剧质感。写实古风电影摄影,午后暖白阳光,低饱和粉绿电影调色,细腻胶片颗粒,浅景深,真实皮肤与布料质感,甜蜜迷人。男主阳光帅气、爱笑;女主白里透红、娇俏灵动。 女主·林晚棠:浅黄襦裙。男主·顾承砚:月白常服。 午后桃林,落英缤纷,石凳。 0.0–3.0s:男主靠桃树闭眼小憩,神情放松。3.0–6.0s:女主踮脚靠近,飞快在他脸颊亲了一下,转身就跑,裙摆翻飞。6.5–10.0s:男主睁眼,一片桃花落在他肩头,他摸着脸颊笑得像偷到糖的孩子,对背影喊:跑什么,我又不吃人!定格在甜蜜。 脸部严格锁定角色图,禁换脸;偷亲点到为止,禁过度亲密;女主逃跑路线连贯,禁瞬移;禁第三人;禁手指异常肢体变形;禁表情跳变;禁字幕水印UI;禁动漫感塑料皮过强HDR。

by @7998l201Source
Hover to preview · click for sound

Costume romance: water sleeves (episode 7)

只参考两张人物角色图的脸部、发型、五官形象(图1=女主·林晚棠角色图,图2=男主·顾承砚角色图),人物身份、脸型、五官、发型、气质必须与角色图严格一致,锁定形象;身材、服装按本集提示词执行。生成一段10秒短视频。 国产古风甜宠影视剧质感。写实古风电影摄影,夜晚烛光暖黄,低饱和电影调色,细腻胶片颗粒,浅景深,真实皮肤与布料质感,唯美。男主阳光帅气、爱笑;女主白里透红、气质出尘。 女主·林晚棠:月白舞衣(广袖),发丝微润。男主·顾承砚:常服。 夜晚练功房,烛光。 0.0–3.0s:女主练舞,水袖翻飞,露出一截皓腕,颈间薄汗在烛光下发光,身姿优美。3.0–6.5s:男主在门口看直了眼,忘了进来。6.5–10.0s:女主发现他,坏笑着用水袖扫过他的脸:好看吗?男主诚实点头,被团扇敲头:登徒子。两人笑作一团。定格在欢乐。 脸部严格锁定角色图,禁换脸;舞蹈唯美,点到为止,禁暴露;水袖飘动自然,禁穿透身体;禁第三人;禁手指异常肢体变形;禁表情跳变;禁字幕水印UI;禁动漫感塑料皮过强HDR。

by @7998l201Source
Hover to preview · click for sound

Along the River During the Qingming Festival, animated in 43 seconds

风格:古画动态活化,北宋工笔,保留原作线条与色彩, 不改成写实照片;缓慢运镜,古风轻柔氛围感,无现代元 素,画面流畅,电影级柔和光影 > 总时长:43 秒 分镜脚本 0-9s|全景慢推:从整幅清明上河图长卷左端缓缓移入,初春汴河郊外,疏林、农田、赶路行人,微风拂动树梢,人物轻微走动,河面泛细碎波纹,画纸肌理保留,淡赭石古画色调,缓慢平移镜头 9-20s|镜头滑向汴河虹桥:重点段落,虹桥下大船船夫奋力撑篙、拉绳,桥上人流往来,挑夫、小贩、骑马官员缓步移动,旗帜轻轻飘动,细节细腻,动作幅度小(古画活化,不夸张) 20-32s|缓慢右移,汴河沿岸街市:街边店铺、茶馆、摊贩,百姓闲谈走动,马车缓缓前行,屋檐灯笼轻晃,烟火气息安静克制,保留原画构图,不新增额外人物建筑 32-43s|长卷收尾缓缓拉远:镜头慢慢向后拉出,重回长卷全景,画面渐柔,完整展现这幅流动的北宋市井画卷,淡柔光,画绢质感

by @duange6099Source

Period drama in one take, 35mm

Excerpt

10-second single continuous take, one unbroken flowing shot, 16:9, hyper-photorealistic live-action Chinese period film, 35mm cinema lens, real shallow depth of field, low-saturation Song painting palette, light film grain, soft warm morning side-light, natural water mist and air perspective, 1080p visual quality. …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
blocks: Camera · 3 timed beats · 3873 characters in the original post
Watch on X
by @PixelAigcSource

Third day as an empress

Excerpt

Muse Video Prompt Format lock: Aspect ratio 9:16 (source 720x1280, 30 fps; generate at 1080x1920, 30 fps) — the output MUST use exactly this 9:16 vertical ratio; no cropping, no reframing, no letterbox change. Total runtime: about 55 seconds in 6 clips. A glossy AI palace fantasy: a modern woman has transmigrated into an empress, and this is day three — a single shameless day of pleasures shot as a lush montage: cherries at dawn, a petal bath, a dragon boat, a lantern festiv …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
blocks: Format lock / Avoid / Identity / Camera · 9 shots · 10612 characters in the original post
Watch on X
by @sandmrkSource
Hover to preview · click for sound

Night market in Northern Song Bianliang, POV

帮我生成一个 60 秒的视频,视频内容是古代人们夜市的生活景象,朝代可以参考北宋东京汴梁。 以下是对于视频的具体要求:: • POV 视角,像逛夜市一样 • 服装、建筑都要尽量符合北宋史实 • 一定要真实,人物和质感都要真实,不要像 AI 生成的那么油腻,要有真实的记录感 不过需要特别注意的是,Muse 的文生视频能力很强,但对于历史,特别是历史建筑或历史细节,仅凭它的训练数据就有点吃力了。如果训练素材没有覆盖,它可能就会失真。这也是为什么大家看到大量 Muse 生成的视频,要么是架空时代,要么是自然风光,最多见的就是西藏雪山,因为这些场景大概率不会出错,而且通过文生视频就能直接实现。 而且 Muse 不像 seedance 2.5 或者 MiniMaxH3 那样,有极强的多图参考或图生视频能力。所以大家也不要想着用参考图来还原生成视频了,我试过很多遍,它几乎没有任何参考能力。 以上这几点大家需要特别注意

by @zhu185178Source

Through the emperor's eyes

Excerpt

Muse Video Prompt Format lock: Aspect ratio 9:16 (source 720×1280, 30 fps; generate at 1080×1920, 30 fps) — the output MUST use exactly this 9:16 vertical ratio; no cropping, no reframing, no letterbox change. Master (include with every clip): Identity & costume lock: The emperor — never seen; the camera IS his point of view for the whole film. …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
blocks: Format lock / Master / Avoid / Identity · 5 clips · 8 shots · 8838 characters in the original post
Watch on X
by @sandmrkSource

Swordsman in white and a woman in purple, 11 shots

Excerpt

第1到11镜的提示词总结如下,通用部分每镜都带:白衣古装剑客+紫裙女子、电影颗粒感、电影级调色。 1.沙漠黄昏沙丘:两人站在一起,风吹衣发,对视,带温柔表情,镜头缓推,暖金色光。 2.沙漠黄昏沙丘ridge:两人并肩走,衣袖裙摆随风飘,她回头一笑,他跟着笑,镜头横向跟拍。 3.沙漠黄昏特写:两人停下、面对面,他轻轻牵起她的手,她抬头轻笑,风吹头发衣服,镜头缓推到面部特写,夕阳渐暗。 4.沙漠黄昏远景:两人牵手走向地平线,金橙色天空下的剪影,镜头缓缓拉远升起,露出整片沙漠。 5.沙漠夜里篝火:两人在星空下并肩坐在篝火边,火光映脸,她轻轻靠在他肩上,他望着星星微笑,镜头缓推。 6.沙漠黎明:第一缕光漫过沙丘,她转圈、紫裙随风扬起、笑得很开心,他温柔地看着她,镜头缓缓环绕,晨光柔和。 …

This is an excerpt. Read the full prompt in the original post →
Full prompt:
607 characters in the original post
Watch on X
by @ddny09Source

How to write great Muse Video prompts

  1. 1Lock the person with one reference sheet. The most-copied format here starts from a single composite image: a headshot on the left and a three-view outfit sheet on the right. The prompt points at it section by section (face from the headshot, outfit from the turnaround) and repeats that the face and outfit must not change in any shot. Through the API, send that sheet as a reference image, not as a first frame.
  2. 2Write the body in time steps and cut on the beat. Those prompts describe each shot in 0.3-second steps (weight shift, where each hand is, where the eyes go) and list the cut points, such as 1.80 s, 3.50 s and 5.10 s, against the beats of the music. "She poses" on its own gets you a stiff loop.
  3. 3For POV, make the camera a person. The boyfriend-POV series opens with the same rule in every episode: the camera is his eyes, and he never appears except for a hand or forearm. Then the action in 0–2 s / 2–5 s / 5–8 s / 8–10 s, one line of dialogue, and a handheld 9:16 phone look.
  4. 4Repeat a block for what must not change. The long English prompts open with a format lock (aspect ratio and source resolution) and a Master block that fixes the character and costume word for word and is pasted into every clip. Dance prompts add a tempo lock: the BPM and the timestamp of every downbeat.
  5. 5Ask for the flaws of a phone camera. Selfie and vlog prompts get their realism by asking for handheld shake, focus breathing, noise-reduction smear, platform compression and 720p, and by banning HDR, studio retouching and a face that stays sharp the whole time.
  6. 6Split anything longer than 20 seconds. Several prompts here describe films of 30 seconds to a minute. On the API each request is 4 to 20 seconds and up to 4,000 characters, so split by clip, keep the character block identical in each request, and edit the clips together.
  7. 7One-liners need the app, not the API. Instructions such as "turn the images in this post into a video" or "remake ten videos in the style of this clip" work in the Muse app because the agent opens the link and writes its own prompt. A video API only sees the text you send, so write the shots out.

Prompt formula

Format (aspect ratio, length) + who (locked by a reference image) + scene + light + camera position + shots written in time steps + style + sound + what to avoid

Example: 9:16, 10 seconds, handheld phone selfie. The woman from the reference image, same face, hair and outfit throughout. A quiet bookshop aisle in the late afternoon, warm window light from the left. 0–3 s: she pulls a book from the shelf and glances at the lens. 3–6 s: she lifts it to hide half her face and laughs. 6–10 s: she lowers it, looks straight into the lens and says "Found it." Slight handheld shake, natural skin texture, the soft sound of pages. Avoid: on-screen text, extra fingers, a second person.

Frequently asked questions

What is Muse Video?

Muse Video is the video model in Meta's Muse AI family. Most people use it inside Meta's Muse app, a chat agent: you describe the video, or paste a long prompt, and it produces the clip. Through apimodels.app the same model is available over an API as muse-video, with the limits listed below.

Who wrote these prompts, and why are some of them excerpts?

Each card credits the creator and links to the original post on X. A prompt is quoted in full when its author invited readers to use it, or when it is 600 characters or shorter; longer prompts are quoted from the beginning, word for word, and marked as excerpts, with the full text in the original post. If you wrote one of these prompts and want it removed or the credit corrected, email us or open an issue on the GitHub repository.

Where can I run these prompts?

In Meta's Muse app, where they were written, or through the API on apimodels.app as muse-video: text, one first frame or one to four reference images in; a 720p clip of 4 to 20 seconds out, 16:9 or 9:16. It is billed at $0.037 per requested second (4 seconds $0.148, 10 seconds $0.37, 20 seconds $0.74); failed tasks are not charged, and not every request succeeds. Clips of up to 10 seconds usually take 1 to 2 minutes.

Why does a long prompt from this page fail on the API?

The API takes prompts of up to 4,000 characters and clips of 4 to 20 seconds. Several prompts here are longer than that or describe a 30-second to one-minute film. Split them by clip, keep the character and costume block identical in every request, and edit the clips together.

How do I keep the same person across shots?

Send reference images: one to four photos of the person keep the face, hair and outfit without forcing the clip to start from any of them. A first frame instead makes the clip start from that exact picture. You can send one or the other, not both. The reference-sheet prompts on this page are written for a single composite image with a headshot and a three-view outfit sheet.

Do the one-line instructions work through the API?

No. Instructions such as "turn the images in this post into a video" rely on the Muse app opening the link and writing its own prompt. The API only receives the text and images you send, so write the shots out or use one of the full prompts instead.

Can I use these prompts commercially?

The prompts belong to their authors. Check the original post before reusing one commercially. For clips you generate yourself, check the terms of the service you generate them with.

Run these prompts on apimodels.app

Muse Video is live here alongside 150+ other image, video, audio and language models — one API, one key, pay as you go, with $0.10 of trial credit on sign-up.

This library is open source on GitHub

The whole collection is on GitHub as Markdown and JSON, one page per prompt, with credits and links to the original posts, plus a page to search and copy them. Prompts are quoted in full when the author invited reuse or the prompt is 600 characters or shorter; longer ones are excerpted from the beginning, with the full text in the original post. The videos stay with their creators and are not re-hosted. Our own notes, titles and data are licensed CC BY 4.0. Open an issue to correct a credit or have a prompt removed.

View on GitHub

Other prompt libraries