Toshi🎬AI動画💫MV制作🎧's banner
Toshi🎬AI動画💫MV制作🎧's profile picture

Toshi🎬AI動画💫MV制作🎧

@Toshi_nyaruo_AI • 2,060 subscribers

🏅 Official @TapNow_AI Creative Partner TapNow "ワンタップの魔法" 💫ラッキー賞⭐ AIドリームC🎇傑作ノミネート賞 CPP/TapNow/hailuo ECP💫klng AI 最新AIを活用したMVや短編アニメを制作。 👇全作品のプロンプト&ワークフロー公開中

Shorts

nijiJourneyV6 & seedance2.0でkawaii系MV🎵 みんなで踊るプロンプトを共有。15秒で5枚のリファレンスを使用💕 ✳️seedance2.0プロンプト Use the uploaded images as the primary visual references for character design, facial style, color palette, graphic motifs, and overall kawaii-chaotic tone. 15-second music-video style animation, ultra cute and hyper pop, fast-paced, candy-colored, chaotic but readable, anime-inspired graphic motion. Main direction: The characters dance in a cute, playful, slightly chaotic “mob dance” / “idol crowd dance” feeling. The motion should feel inferred naturally from the reference images, not rigid choreography. Emphasize fast switching expressions, group-like energy, rapid cut transitions, and a dense pop visual atmosphere. Visual style: Pastel neon palette, pink, cyan, lemon yellow, mint, lavender. Bold clean outlines, flat shading, sticker-like icons, bows, flowers, sparkles, spirals, abstract shapes, pop symbols, glitchy accents, halftone dots, split panels, manga-like framing, layered collage feeling. Cute and stylish chaos, not horror, not grotesque. Character motion: Generate adorable dance movement with small bouncy steps, side-to-side body sway, quick hand poses, synchronized hops, idol-style gestures, playful pointing, little spins, shoulder pops, head tilts, wink poses, cheerful bouncing, cute rhythmic stepping.The dance should feel like a spontaneous cute flash-mob or idol crowd routine, with repeated shared gestures, group energy, and playful synchronized timing. Include moments that feel like a crowd dance or mob dance, even if only one or a few characters are visible at a time. The dance should feel energetic, spontaneous, and rhythm-driven. Expression direction: Rapid expression changes: smile, wink, surprised face, excited open-mouth face, mischievous grin, hypnotic stare, sparkling eyes, dizzy spiral-eye mood, overjoyed face, playful chaos. Expressions should switch quickly with the cuts, giving a hyperactive kawaii feeling. Editing / camera: Very fast-cut visual rhythm. Use rapid cut-ins, jump cuts, smash zooms, push-ins, pull-backs, diagonal framing, split-screen panels, close-ups of faces, occasional medium shots for dance, and layered pop composition. Cuts can change every 0.2 to 0.8 seconds. Alternate between close-up face shots, upper-body dancing, and brief group/crowd-energy compositions. The camera should feel lively and music-synced. Scene flow: 0–3s: Introduce the character(s) with fast close-ups, blinking, cute smile, eye highlights, bows/flowers/icons popping in, fast panel cuts. 3–6s: Start the dance with small synchronized idol-like motions, side steps, hand poses, bouncing shoulders, quick expression switches. 6–9s: Increase the chaos. More split panels, more characters or crowd-energy feeling, fast alternating expressions, quick hops, spins, and rhythmic pose changes. 9–12s: Peak energy. Cute mob-dance vibe, dense visual layering, multiple rapid cut-ins, close-up reaction faces, synchronized bounce and gesture-heavy movement. 12–15s: Final climax. Maximum kawaii chaos with energetic dancing, smiling faces, wink, big pose finish, layered pop symbols exploding around the frame, ending on a strong cute final pose. Important priorities: Keep the characters cute and appealing at all times. Preserve readability of faces and silhouette. Let the dance and expressions feel naturally inferred from the references. The chaos should come from editing, framing, layered motifs, and rapid expression changes, not from broken anatomy or visual confusion. Negative prompt: horror, dark tone, realistic style, grotesque face, body deformation, extra limbs, broken hands, scary expressions, dull colors, muddy palette, slow motion, empty background, overly realistic physics, unreadable face, low energy, depressing mood.Make the choreography feel partially AI-inferred from the visual mood of the references: cute, chaotic, rhythmic, slightly unpredictable, but always charming and musically coherent.

nijiJourneyV6 & seedance2.0でkawaii系MV🎵 みんなで踊るプロンプトを共有。15秒で5枚のリファレンスを使用💕 ✳️seedance2.0プロンプト Use the uploaded images as the primary visual references for character design, facial style, color palette, graphic motifs, and overall kawaii-chaotic tone. 15-second music-video style animation, ultra cute and hyper pop, fast-paced, candy-colored, chaotic but readable, anime-inspired graphic motion. Main direction: The characters dance in a cute, playful, slightly chaotic “mob dance” / “idol crowd dance” feeling. The motion should feel inferred naturally from the reference images, not rigid choreography. Emphasize fast switching expressions, group-like energy, rapid cut transitions, and a dense pop visual atmosphere. Visual style: Pastel neon palette, pink, cyan, lemon yellow, mint, lavender. Bold clean outlines, flat shading, sticker-like icons, bows, flowers, sparkles, spirals, abstract shapes, pop symbols, glitchy accents, halftone dots, split panels, manga-like framing, layered collage feeling. Cute and stylish chaos, not horror, not grotesque. Character motion: Generate adorable dance movement with small bouncy steps, side-to-side body sway, quick hand poses, synchronized hops, idol-style gestures, playful pointing, little spins, shoulder pops, head tilts, wink poses, cheerful bouncing, cute rhythmic stepping.The dance should feel like a spontaneous cute flash-mob or idol crowd routine, with repeated shared gestures, group energy, and playful synchronized timing. Include moments that feel like a crowd dance or mob dance, even if only one or a few characters are visible at a time. The dance should feel energetic, spontaneous, and rhythm-driven. Expression direction: Rapid expression changes: smile, wink, surprised face, excited open-mouth face, mischievous grin, hypnotic stare, sparkling eyes, dizzy spiral-eye mood, overjoyed face, playful chaos. Expressions should switch quickly with the cuts, giving a hyperactive kawaii feeling. Editing / camera: Very fast-cut visual rhythm. Use rapid cut-ins, jump cuts, smash zooms, push-ins, pull-backs, diagonal framing, split-screen panels, close-ups of faces, occasional medium shots for dance, and layered pop composition. Cuts can change every 0.2 to 0.8 seconds. Alternate between close-up face shots, upper-body dancing, and brief group/crowd-energy compositions. The camera should feel lively and music-synced. Scene flow: 0–3s: Introduce the character(s) with fast close-ups, blinking, cute smile, eye highlights, bows/flowers/icons popping in, fast panel cuts. 3–6s: Start the dance with small synchronized idol-like motions, side steps, hand poses, bouncing shoulders, quick expression switches. 6–9s: Increase the chaos. More split panels, more characters or crowd-energy feeling, fast alternating expressions, quick hops, spins, and rhythmic pose changes. 9–12s: Peak energy. Cute mob-dance vibe, dense visual layering, multiple rapid cut-ins, close-up reaction faces, synchronized bounce and gesture-heavy movement. 12–15s: Final climax. Maximum kawaii chaos with energetic dancing, smiling faces, wink, big pose finish, layered pop symbols exploding around the frame, ending on a strong cute final pose. Important priorities: Keep the characters cute and appealing at all times. Preserve readability of faces and silhouette. Let the dance and expressions feel naturally inferred from the references. The chaos should come from editing, framing, layered motifs, and rapid expression changes, not from broken anatomy or visual confusion. Negative prompt: horror, dark tone, realistic style, grotesque face, body deformation, extra limbs, broken hands, scary expressions, dull colors, muddy palette, slow motion, empty background, overly realistic physics, unreadable face, low energy, depressing mood.Make the choreography feel partially AI-inferred from the visual mood of the references: cute, chaotic, rhythmic, slightly unpredictable, but always charming and musically coherent.

13,761 görüntüleme

Videos

Toshi_nyaruo_AI's profile picture

[PR]MiniMaX H3でOriginalリリックモーションMV🎞️ 🎵TapNow「UNSEEN WORLD/まだ見ぬ世界」グローバル・ミュージックビデオ・コンテスト応募作品🎶 Tapnowのワークフローを使って、可愛い女の子のスローなHIPHOP MVを制作。 すべての画像とプロンプトはワークフローに。 リプ欄から。プロンプトも共有👇 ✳️MiniMaX H3プロンプト 格式:10.69秒,16:9横屏,24fps,动画角色×实景艺术装置的表演MV,第1段(共13段,对应歌曲0:00.00—0:10.69)。音频1即本段的完整配乐与人声。 参照:图像1是唯一歌手兼行走者"Yui"的严格身份与服装参考——它是一张角色设定图,只取人物本身:正面、侧面、背面的三视图用于她的转身与背影的一致性,右侧的表情格用于她唱歌与回头时的表情;设定图上的文字、色卡、边框与排版一律不出现。图像2是世界W20(0.00—10.69秒的场景):白色桌面上摊开的笔记本:粉色横线的纸页上画着放大的眼睛与鼻子,一支黑色钢笔搁在右页上,桌面左侧铺着粉色,几张黄色便签;俯视;只取空间、材质、配色与透视。音频1是本段的完整配乐,从第一帧起原样、同步使用;音频1是安静的前奏:没有鼓,4.32—6.08秒有一声闭口哼唱(mmm),9.80秒之后几乎无声;本段没有歌词。 人物锁定:Yui的设计在每一帧完全一致:淡金色(接近铂金)的长直发,齐眉平刘海,头发在右后方扎成一束低侧马尾并系一条红色丝带,发间夹着一缕细细的红色发丝;深红色的眼睛;红唇;白皙皮肤;左耳一串银色小坠饰耳环;oversize的红色连帽外套(半透明的红色尼龙质感,衣身透出更浅的几何色块,袖子长过手腕);胸前一条黑色带扣的斜挎背带;外套里是黑色长款T恤;腰间垂着几条红色织带;白色宽松工装裤(多口袋,裤脚收口);红白黑三色高帮运动鞋,鞋上不出现任何品牌标志。她的全身自由行走、转身与做动作:髋、膝、脊柱、重心转移全部允许。任何景别下五官保持一致。 视觉风格:Yui按图像1的二维动画画风渲染——干净的线稿、平涂上色加柔和渐变、无写实皮肤纹理;她以实体存在于参考空间里,脚下有柔和的接触阴影,身上的受光方向与空间一致,靠近粉墙时外套的高光带粉色反光。空间保持各参考图的摄影级3D装置质感:哑光白、饱和的桃红与黄、黑色的涂鸦纹样。高调曝光:白是白、黑是墨黑、粉饱和;顶部均匀的白色天光。24fps干净运动,无长拖影。 镜头:全片只有一个方向——Yui始终向画面深处(消失点)行走,摄影机从她身后跟随(时尚短片摄影师的稳定器手法,平稳、果断);基本机位在她身后约2.5米、略低于肩高,24mm,帽顶到球鞋全部入画;她回头唱歌时从靠近摄影机一侧的肩膀上方回望镜头;她转身面向镜头时依旧倒退着向深处走,摄影机以同速向前跟进;消失点永远在她前方,绝不拍她迎面走来。每个时间块是一个连续镜头;无淡入淡出、叠化、闪白、慢动作、变速或镜头滚转。本段硬切只发生在5.75秒。 步伐:步伐锁定在音乐的节拍上——85 BPM,每拍(0.706秒)落一步,右脚落在每小节的第1拍与第3拍,左脚落在第2拍与第4拍;步幅稳定,肩与髋反向摇摆,双臂自然摆动,下巴微抬,一种慢而笃定的走秀步。本段开场第一帧:她站在起点、左脚在前;结尾帧:她的左脚正要落地、处在跨步中。 口型同步:本段没有歌词,她不唱,嘴唇闭合。 时间结构(本段内秒数;85 BPM,一拍0.706秒,小节头在0.10、2.93、5.75、8.58): [0.00—5.75|世界W20,固定机位] 音乐是安静的前奏,没有鼓。高角度俯视整本摊开的笔记本(图像2的构图):Yui以微缩的比例站在右页的下缘——她的身高大约等于三条粉色横线的间距,笔记本对她来说像一片操场——背对镜头,0.10秒起沿着粉色横线的方向向页面上缘(画面深处)走,每拍一步。她的左侧是画在左页上的巨大眼睛(静止的画),右前方是搁在页面上的黑色钢笔,像一根倒下的柱子。摄影机固定不动,她在画面里逐渐变小。4.32—6.08秒音频里有一声闭口的哼唱(mmm):她的嘴唇闭着,随哼唱轻轻点头两次,不开口。 [5.75—10.69|世界W20,贴地跟随] 在第3小节头硬切:机位降到她的尺度,在她身后约2.5米、略低于肩高,24mm,跟随她前进;粉色横线在她的球鞋下向后掠过,右侧那支巨大的钢笔的笔杆从画右滑过,左前方纸页上巨大眼睛的下睫毛像一排黑色栅栏。她的步伐稳定:每拍一步,右脚落在第1、3拍,左脚落在第2、4拍;肩与髋反向摇摆,双臂自然摆动,不回头。9.02与9.72秒各有一声轻击,她的头随之各点一次。9.80秒起音乐几乎无声,她继续走,摄影机继续跟随。结尾帧(10.69秒)她的左脚正要落地、处在跨步中——下一段从这一步接上。 表演:安静、好奇;她不唱,嘴唇闭合,只在哼唱处轻轻点头。 编辑与连续性:2个连续镜头,硬切只在5.75秒,各镜头内部没有剪辑;切镜前后Yui的服装、发型、妆容完全一致;开场第一帧承接上一段的步伐,结尾帧留给下一段接续。 声音:音频1作为全部配乐与人声,从第一帧起原样同步使用,并作为演唱口型、乐句与换气的参考。不添加任何音乐、音效、人声或环境声。 画面文字:本段不出现任何文字;画面中不得出现可读单词、字母、logo、中文或乱码字形,参考图里的涂鸦笔画保持不可辨读。 限制:Yui是画面中唯一的人,参考图里的人物一律不出现;她手里没有任何物件;不出现品牌标志;无淡入淡出、叠化、闪帧、慢动作或变速;无镜头光斑、粒子消散、液化;不在墙上新增眼睛、人脸或文字;参考空间的结构与陈设不变形。目标:一支预算充足的单人走秀式MV——一位动画角色在真实的艺术装置里一路向前走,K-pop表演视频的自信与画廊级装置短片的质感;绝不是幻灯片,绝不是静止的时尚照片。 プロンプトは、中国語のほうが1/3に圧縮できます。 ✳️今回使用したツール 💠動画:seedance2.5、2.0 💠画像:nijiJourney V8.2、GPT-image2 💠音楽:SUNO 💠音声:なし 💠編集:CapCut 💠脚本:ClaudeCode Fable5.1 ✳️今回良かった点 ClaudeCodeで曲の分割、画像の選定、H3のプロンプト提案まで行ったため、動画化が楽にできました。 ✳️残念だった点と H3がアニメを3Dと認識することがあって、再生成に。 予め2Dアニメと指定したほうがよかったです。 このような機会を設けて頂いたTapnowさまに感謝いたします😊

Toshi🎬AI動画💫MV制作🎧

34,776 görüntüleme • 1 ay önce

Toshi_nyaruo_AI's profile picture

[PR] nijiJourney & seedance2.0🪩 TapNowAIのワークフローを使って、「Collage Animation & Lyric Motion」のMVを作成しました。 スピード感ある映像と音楽をお楽しみください😆 以下プロンプトも共有しています。 リリックモーション部分も全部seedance2.0製です・ ✳️今回の作成手順 1.SUNOで音楽を生成 2.nijiJourneyで元画像を作る 3.5枚のnijiJourney画像をリファレンスで動画生成 4.リリックモーションはChatGPTとチャットで作成 ✳️seedance2.0 プロンプト abstract art animation, hand-drawn, emotional kinetic transformation. through are five cyberpunk and glitch-art compositions featuring neon pink, cyan, magenta, electric blue color palettes, digital glitch artifacts, pixelated distortions, heterochromatic glowing eyes, data-moshing effects, and claustrophobic intensity. Extract every form, motif, color, line quality, texture, rhythm, and emotional tension from the references. The animation must feel fast, alive, unstable, and emotionally charged. Every transformation seamless and continuous. No hard cuts. No static pauses except single-frame impact holds. Entire composition including background constantly transforms. All elements behave as if pulled by memory, gravity, heat, sound, and emotion simultaneously. [0-1.5s] A central abstract figure appears as if already in motion. Its inner color pulses outward in uneven emotional waves, while its outline tears away in multiple directions. The background bends around the figure like soft paper under pressure. Fine hand-drawn textures crawl across the surface faster than the main form moves, creating tension between body and skin. [1.5-3s] The detached outlines accelerate and become nervous thread-like forms. The figure's color core stretches into sharp ribbons and liquid stains simultaneously. Some ribbons snap back, others whip forward, each leaving a trembling residue. Empty spaces between moving parts ignite into new shapes, as if the composition is creating forms to fill its own emotional gaps. [3-4.5s] All forms suddenly surge diagonally across the frame. One large shape folds over itself like fabric, but the fold reveals a completely different texture beneath: grain, chalk, wet ink, and scraped paint all visible at once. The background follows the fold, twisting into a new color field. Smaller forms are dragged behind the motion, stretching into speed lines that remain alive and continue transforming. [4.5-6s] The composition fractures into several emotional forces: one calm, one violent, one fragile, one ecstatic. Each force pulls color from the others. Shadows appear before the objects that cast them, moving ahead like predictions. Original forms chase their own shadows, but the shadows mutate faster, becoming brighter, thicker, and more dominant than the objects. [6-7.5s] A rapid chain reaction begins. Every collision between forms produces a new motif taken from the references: fragments, symbols, textures, silhouettes, stains, lines, and color fields. These new motifs immediately accelerate in different directions. Trails do not simply fade — they harden into new bodies, then melt again, then split into smaller emotional echoes. [7.5-9s] The entire frame compresses toward a single invisible point near the lower center. All lines, colors, textures, shadows, and background layers squeeze inward at different speeds. Hold maximum compression for one single frame. Then everything explodes upward and outward with vertical smears, wobbling contours, and overshooting motion. Each element lands in a new position but continues vibrating from impact. [9-10.5s] Textures begin migrating between forms like exchanged emotions. A rough dry texture enters a fluid form, making it move in broken angular steps. A liquid texture enters a rigid form, causing it to sag, drip, and breathe. A glowing color texture passes into the background, making the entire environment pulse. Every form changes behavior based on the texture it receives. [10.5-12s] A cascade of rotations crosses the frame. Each form flips, twists, or turns inside out, revealing a hidden back face with a dramatically different color and emotional quality. Revealed faces reach toward neighboring forms like hands, hooks, flames, or waves. When touched, the next form rotates immediately, continuing the cascade faster and faster until the entire frame has transformed into a new emotional world. [12-13.5s] Boundaries dissolve everywhere at once. Forms merge, reject each other, separate, then merge again. New hybrid shapes inherit colors, textures, and motion behaviors from their parents but never become identical to them. The background no longer sits behind the forms — it becomes one of the forms, pushing forward, swallowing edges, and releasing new figures from within itself. [13.5-15s] Every previous process returns simultaneously at maximum speed: outlines detach, colors seep and drip, textures migrate, shadows lead, forms chase, trails solidify, hidden faces rotate, boundaries dissolve, backgrounds fold, and hybrid shapes multiply. Each element performs multiple transformations at once. Final second feels emotionally overloaded but visually intentional — a fast, hand-drawn abstract storm where every reference has been fully absorbed and transformed until the last frame. これを元にいくつかプロンプトを変えて生成しています。 ✳️MV作成で良かった点 映像をseedance2.0に作成してもらったので、他の作業に集中できた。 リリックモーションは、ChatGPTに歌詞を渡して考えてもらってます。 ✳️MV作成で残念な点 リリックモーションの部分もseedance2.0で作成したため、完全に音ハメできませんでした。 もっと細かく生成して調整したほうがよかったかもです。 また、クロマキーでリリック部分を作成したため完全に緑を除去できませんでした。 何かいい方法ないかなぁ… 最後に、このような機会を設けて頂いたTapNowAIさんに感謝致します☺️

Toshi@ニャルオAI

14,282 görüntüleme • 4 ay önce

Daha fazla içerik yok.