
アユネオ
@Ayu_AI_0912 • 3,712 subscribers
AI動画クリエイター|バズ部×DomoAIコンテスト最優秀賞|CPP:Vidu / Domo AI / Hailuo AI など|AIアイドル「くらげちゃん」育成中|※アイコンはアユネオ本人です|元NHK北海道キャスター|お仕事のご連絡はDMまで
Shorts
DomoAIでパルクールアニメ研究中【PR】 ――――― 2秒ごろかっこいいから見て! ――――― ▼プロンプト▼ 15-second cinematic parkour action video, 16:9, 1080p, 8 hard cuts. The protagonist is the 2D anime cat-girl character from image_1. Preserve her face, hairstyle, costume, colors, proportions, and all character features exactly in every cut. She exists naturally within a live-action photorealistic modern Japanese city. Setting: contemporary Japanese urban streets and rooftops during bright daytime — concrete buildings, narrow alleys, staircases, metal railings, rooftop ledges, signage, and dense city architecture typical of Tokyo, Shibuya, Yokohama, or Yokosuka. Clear natural daylight, blue sky, and crisp shadows. Shot 1 [00:00–00:01.20]: Low rear 3/4 tracking shot in a narrow alley. She crouches, then sprints toward a low concrete wall. Directional speed blur trails her legs, arms, hair, and costume. Shot 2 [00:01.20–00:03.60]: Front 3/4 low-angle shot. She performs a forward flip over the wall. Full body clears the obstacle. Rotational speed blur follows the flip while her face and silhouette remain readable. Shot 3 [00:03.60–00:04.93]: True side close shot near ground. She lands into a running forward roll, then rises immediately. Brief motion blur during the roll. Shot 4 [00:04.93–00:07.33]: Low side rooftop shot. She accelerates and performs a large forward flip over a parapet against the bright city skyline. Strong directional speed blur emphasizes forward momentum. Shot 5 [00:07.33–00:08.67]: Near-overhead shot. She lands and rolls along the rooftop path. Her body stays on the surface. Blur follows the direction of the roll. Shot 6 [00:08.67–00:11.07]: Retreating front-facing camera. She charges toward a railing or concrete barrier and performs a forward flip. Slight handheld shake and controlled speed blur. Shot 7 [00:11.07–00:12.40]: Rear diagonal low tracking shot. She performs a quick roll, then sprints toward the final obstacle. Strong speed blur trails her movement. Shot 8 [00:12.40–00:15.00]: Hero climax shot. She performs a maximum-height forward flip over a large concrete ledge. Camera arcs around her during rotation. She lands and runs out of frame with a final speed-blur trail. Global rules: Apply directional speed blur mainly to the protagonist during fast movement. Keep the background relatively sharp. Preserve clear face, silhouette, anatomy, and costume at jump apexes and landings. No duplicate limbs, ghost faces, melted anatomy, T-poses, teleportation, floating, or body penetration. Keep the 2D anime character style consistent against the live-action Japanese urban background. ――――― 今回は、DomoAIを使用して生成しました✨ Seedance2.0 Fastのモデルで、 キャラクターシート参照、720pの設定で出力。 普段はDomoAIを リップシンクをメインで超超愛用していますが、 Seedance2.0も使えるのでさらに便利! #DomoAI
20,371 views
パルクール動画の研究中【実写×アニメ】 ―――― 爽⭐快⭐感! 今回は、Flova AIにプロンプト生成を 手伝ってもらいました! ※使用モデル:Seedance2.0 ▼プロンプト▼ 15-second cinematic parkour action video, 16:9, 1080p, 8 hard cuts. The protagonist is the 2D anime cat-girl character from image_1 — short lime-green hair with cat ears and a teal-green headband, bright blue eyes, delta-shaped hollow triangle tie with yellow outline, light blue sleeveless dress with zigzag yellow hem, white long-sleeve undershirt, light blue thigh-high stockings with mechanical robotic knee pads bearing triangle markings, pink ankle boots with zigzag triangle sole markings, pink randoseru backpack with yellow pencil holder sticking out the top, a robotic segmented cat tail with a gold triangle tip, and small delta-symbol earrings. Her face, hairstyle, costume, and all character features must be preserved exactly in every cut. The 2D anime-style character coexists naturally within a live-action photorealistic real-world modern Japanese urban environment. Setting: real contemporary Japanese city streets — concrete buildings, narrow urban alleyways, rooftop ledges, exterior staircases, metal railings, concrete walls, urban barriers, overhead signage, and dense city architecture typical of modern Tokyo, Shibuya, Yokohama, or Yokosuka. Natural daylight or golden-hour city lighting. Shot 1 [00:00–00:01.20]: Low rear 3/4 tracking shot, ground-level camera nearly scraping the pavement of a narrow urban alley. Protagonist crouches then explodes into a sprint toward a low concrete wall. Camera follows close behind. Shot 2 [00:01.20–00:03.60]: Front 3/4 low-angle follow shot. Protagonist launches into a forward flip over the first concrete wall. At peak, full body clears the obstacle. Cinematic framing against urban buildings. Shallow depth of field. Shot 3 [00:03.60–00:04.93]: True side close shot near ground. Landing flows seamlessly into a running forward roll — shoulder-to-back weight transfer, rises immediately. Full body in frame. Shot 4 [00:04.93–00:07.33]: Opposite low side angle on rooftop. Protagonist accelerates and launches a large forward flip over a rooftop parapet. Ledge in foreground, protagonist soars against open city skyline. Shot 5 [00:07.33–00:08.67]: Near-overhead bird's-eye shot. Protagonist lands and rolls along the urban path. City architecture visible around her. Body stays on surface. Shot 6 [00:08.67–00:11.07]: Retreating front-facing follow camera. Protagonist charges a staircase railing or concrete barrier, forward flip captured from the front. Camera retreats with slight handheld shake. Shot 7 [00:11.07–00:12.40]: Rear diagonal close tracking. Quick forward roll then sprint toward final obstacle. Low camera, handheld feel, protagonist fully in frame. Shot 8 [00:12.40–00:15.00]: Hero climax shot. Maximum-height forward flip over a large concrete ledge against the Japanese city skyline. Camera arcs from front 3/4 to opposite side during rotation. Protagonist lands and runs powerfully out of frame. Global rules: No T-poses, no teleportation, no body penetrating obstacles. Character appearance identical in every cut. 2D anime character style preserved against fully live-action photorealistic modern Japanese urban background.
21,337 views
AIにほぼ丸投げしたショートアニメ【実験】────────────── 画像:Midjourney, Higgsfield Cinema Studio 動画:Vidu Q3 ────────────── ▼制作フロー ①MidJourneyで一枚画像を生成 ↓ ②Higgsfield Cinema Studioの What's nextで9個の画像を生成 ↓ ③Full grid as 1 imageで1枚の画像として保存 ↓ ④Vidu Q3で生成! ────────────── 💡コメント 9枚の画像を1枚として渡すことで、 テンポよく絵が変わる動画が生成できました。 あと、Viduさんならではの表情が 生き生きとしている点も しっかりモデルに反映されていて素晴らしい!
31,399 views
Videos
No more content to load