Загрузка видео...
Не удалось загрузить видео
This Animation turned out cool 🔥 Seedance 2.0 on Higgsfield Full open-sourced prompts and assets below Prompt: Generation 1 Aoi = Image 1 · Kaijin = Image 2 · Mio = Image 3 · Ren = Image 4 · Classroom = Image 5 All shots take place in the... show more
34,375 просмотров • 2 месяцев назад •via X (Twitter)
Комментарии: 0
Нет доступных комментариев
Здесь появятся комментарии из оригинального поста
![Used Product Commercial Skill to create this video on FlovaAI FlovaAI_Japan prom SHOT 1 [0:00–0:03] — 3s, real-time Extreme close-up: a single perfect golden-brown fried mandu (Korean dumpling), triangular fold, sitting on the railing of a 10th-floor officetel balcony in Seoul. Bright midday sun catching every crisp fried edge, steam rising gently. A small dish of soy-vinegar dipping sauce sits right beside it, close to the mandu. SHOT 2 [0:03–0:05] — 2s, real-time A pigeon lands on the railing a foot away. It looks at the mandu, tilts its head, takes one casual step closer. Its wing brushes the sauce dish. SHOT 3 [0:05–0:06] — 1s, real-time The mandu and the sauce dish both wobble from the nudge. They tip together and fall off the edge of the railing. SHOT 4 [0:06–0:10] — 4s, slow motion Wide shot from directly across the street at 10th-floor level: the mandu and sauce dish tumbling outward, rotating end over end, catching the sunlight on every turn. Behind them, the building facade — a tall Seoul apartment block, muted grey-blue exterior, laundry hanging on a few balconies. The mandu is a tiny golden triangle falling against the building. SHOT 5 [0:10–0:13] — 3s, real-time Ground level wide shot: a busy Seoul street in midday sun. Pedestrians with shopping bags, a delivery scooter idling at the curb, a tteokbokki/odeng street cart with an ajumma stirring a pot, a dog sleeping in a patch of sun, an elderly man reading a newspaper on a bench. Ordinary day, nobody aware anything is falling. SHOT 6 [0:13–0:15] — 2s, real-time Close-up on the sleeping dog: one ear twitches, then both go up. Nose starts working. One eye opens, pupils tracking something falling. The dog slowly rises, never looking away from above. SHOT 7 [0:15–0:17] — 2s, real-time Close-up on the cart ajumma: her stirring spoon slows, then stops. She looks up, eyes widening, and slowly sets the spoon down on the cart edge. SHOT 8 [0:17–0:19] — 2s, real-time Close-up on the newspaper man: a small triangular shadow crosses his page. He lowers the newspaper and looks up, his glasses catching the sunlight. SHOT 9 [0:19–0:23] — 4s, slow motion Wide shot of the full street: the mandu and sauce dish visible as tiny falling shapes above the crowd. Below, reactions ripple outward — the dog now standing, the ajumma craning her neck, the newspaper man on his feet, the delivery driver stepped off his scooter looking up, a vegetable vendor shielding her eyes with one hand. SHOT 10 [0:23–0:25] — 2s, real-time A second pigeon flying past at around the 5th-floor level narrowly dodges the falling mandu, does a startled double-take mid-flight, and veers off. SHOT 11 [0:25–0:29] — 4s, extreme slow motion Extreme close-up: the mandu now three feet from the ground, rotating slowly, every crisp fried ridge sharp in the light, a faint trail of steam still lifting off it. The sauce dish falls a foot above it, tilting but staying upright. SHOT 12 [0:29–0:31] — 2s, real-time Ground-level close-up: the dog's mouth is open, perfectly positioned. The mandu drops directly into it. The dog closes its mouth. The sauce dish lands upright on the pavement beside the dog with a small click. SHOT 13 [0:31–0:34] — 3s, real-time The dog sits down, chews twice, swallows. It licks its nose once, then glances down at the sauce dish, then up at the silent, staring crowd. SHOT 14 [0:34–0:40] — 6s, real-time Wide shot: total silence on the street for a beat. Then the dog lies back down in its sunny spot and closes its eyes. The crowd slowly breaks and goes back to what they were doing — the ajumma picks her spoon back up, the newspaper man sits and lifts his paper, the delivery driver gets back on his scooter. SHOT 15 [0:40–0:45] — 5s, real-time Overhead, back on the 10th-floor balcony: the first pigeon is now sitting exactly where the mandu used to be, looking down at the street below. Bright midday sun, crisp shadows. Hold on the pigeon as the shot settles, closing the sequence. #Flovaai #Flovacpp](https://image.24vids.com/tw-2078857994008433022/amplify_video_thumb/2078857695021666305/img/NEYC4PFuvPQ3jkZV.jpg)
![-- What holds it together -- ✂️PAPER CUTS.- When the image is the end ⤵️ What you bring to life is the journey towards the image: how the pieces come to be as they are. The movement is the idea, and your image in Seedance is the final frame. ---------------------------------------------------- What happens to the object? 1⃣ By the time the object TRANFORMS into something else. It takes place in a continuous shot, a single camera that zooms in slowly and never cuts away. A cut would break the transformation; the hypnotic effect lies precisely in the fact that it doesn’t flicker. Template.- [@.RE IMAGE] is the LAST frame. [GLOBAL] [Technique + light + backdrop + focus]. [Real materials]. One continuous hypnotic transformation — a single take, no cuts. The same [OBJECT A] does not appear in pieces; it [VERB: melts / folds / blooms / dissolves] into [OBJECT B]. Slow surreal dreamlike drift, one unbroken slow push, slight stop-motion shimmer, no snapping. 0-1s: [state A, intact and recognizable]. 1-2.5s: [the change begins — "the same material begins to..."]. 2.5-3.5s: [the change at full — "...becomes..."]. 3.5-5s: [it settles]. The push eases to rest. Locked, exact match to the last frame. [LOGIC RULE] one continuous same-lens push, never cutting. [A] morphs into [B], [details that must not deform] stay legible, no warping. hypnotic drift. SFX: [a sound that also transforms]. no music, normal speed. 2⃣ When one thing LEADS to another, we need each step to be a link in the chain of causality. Template.- [@.RE IMAGE] is the LAST frame. [GLOBAL] [Technique + light + backdrop + focus]. [Real materials]. Hypnotic stop-motion paper cadence, slight frame-step, brisk causal montage, ~1.5s per shot, no naturalistic motion, no slow-mo. [cut] [shot + camera] / [carries on from previous cut] / [ACTION: what it DOES, not how it looks]. SFX: [beat-anchored hit]. [cut] ... (link 2 — chains from link 1) [cut] ... (link 3) [cut] ... (link 4) [cut] ... ease back to reveal / [link 5]. Locked, exact match to the last frame. SFX: ... [LOGIC RULE].- [materials], [what must NOT happen], no warping, [text legible if any]. ~1.5s per shot, no slow-mo. no music.](https://image.24vids.com/tw-2071482284088205652/amplify_video_thumb/2071481174329843712/img/etabMqU1N1Odoo3F.jpg)
 styled as a high-school senior — long straight pastel pink hair with center part and face-framing layers, pale makeup, glossy lips, pastel pink short-sleeve school blouse, navy ribbon bow, pastel pink mini skirt, white crew socks, chunky white sneakers, small blue name tag on her chest. She walks the center aisle carrying a stainless 5-compartment lunch tray in both hands. Tray contents: mound of white rice, spicy red tteokbokki cylinders, a pile of kimchi, seasoned green namul, and a small metal soup bowl of red stew. Spoon and chopsticks rest on the tray. Shot 1 (0–1s): Medium-wide tracking shot. She walks straight toward camera down the aisle, calm expression, tray held level at waist height. Background students laugh and eat. Shot 2 (1s): Tight low insert of her feet. She scuffs the heel of her left white sneaker against the polished floor, then plants both feet. Shot 3 (2s): Medium close-up of her face as she looks up, slightly startled, hair swinging. Shot 4–6 (3–6s): Slow-motion VFX food sequence. She tosses the tray upward. The tray and utensils hang in mid-air. Tteokbokki pieces, kimchi, and namul lift off the compartments and float in a neat horizontal line above the tray, as if gravity paused. Cut to overhead: food settles perfectly back into each compartment; soup bowl stays upright, nothing spills. Shot 7 (7s): Wide. She drops into a fast back handspring / cartwheel on the cafeteria floor, skirt flipping, one sneaker kicking high. Students at nearby tables freeze and stare. Shot 8 (8s): She lands spinning, hair whipping, and catches the falling tray and utensils in one fluid motion without dropping food. Shot 9–11 (9–11s): Close-ups of hands catching chopsticks and spoon, then a hero beauty shot of the completed tray held out toward camera — rice, tteokbokki, kimchi, namul, and stew all perfectly arranged. Shot 12 (12s): Cut to a table of boys. Handsome dark-haired boy in white shirt and navy tie turns, mouth open in shock; friends around him gape. Shot 13–14 (13–14s): Tight beauty close-up of the heroine’s face, staring into camera, then a tiny knowing smirk. Shot 15–20 (15–20s): She walks past the shocked boy’s table, tray in her left hand, glancing down at him. Soft line of dialogue in Korean, subtitled: “Let’s eat and see.” He looks down, embarrassed. She keeps walking. Shot 21 (21s): Rear tracking shot as she walks away down the aisle, long hair and navy skirt, cafeteria buzzing again behind her. Style notes: high-end K-drama cinematography (something like a glossy teen romance / school fantasy), practical cafeteria set, subtle slow-motion only on the floating-food and flip beats, clean VFX so the food never smears or looks cartoonish, no logos, no on-screen text except optional Korean subtitle on the one line. Negative: messy spills, broken tray, Western cafeteria, adult office clothes, exaggerated anime faces, shaky phone footage, watermarks.](https://image.24vids.com/tw-2100836177821483349/amplify_video_thumb/2100835484088016896/img/xDHb7YI8Yz7fc0_q.jpg)
![卧槽，牛逼了。 同样的提示词效果居然不一般。💪💪 工具：MiniMax H3，也可以使用在线工具如： 不知火舞第一弹V2👇 第一弹提示词： --- For the target video, at 0.00 seconds into the target video, (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] 2D-animated, retro arcade fighting-game character art style blended with a clean macOS desktop scene, exactly as established in : an arc-shaped light-band wallpaper sweeps from deep blue-violet at the lower left to orange-red and magenta at the upper right over a mirror-like reflective ground; two vertical columns of glossy rounded-square application icons stand on the left half — each icon is a clean pictogram with NO text label beneath it: the first column shows from top to bottom a blue smiling face, a red-yellow-green ring around a blue center dot, a white "N" block in a dark frame, a light-blue infinity-style ribbon, a dark tile with blue letters, an amber tile with yellow script, a purple tile with white letters, and green arcs inside a circle; the second column shows two white chat bubbles on green, a penguin on white, a white paper plane on blue gradient, four colored squares in a grid, a blue-green spiral ring, a red play triangle, colorful pinwheel petals, and a white "A" brushstroke on blue — on the right stands the brown high-ponytail young woman with white horn-like hair ornaments, wearing a red high-slit qipao-style fighting outfit with a large white waist knot trailing red-floral ribbons and white-tassel beads in her hair, black fingerless gloves and red-black heeled sandals; she holds an open white fan with red trim hanging behind her hip while one hand rests on her waist, gazing back over her shoulder. The camera pushes in with small amplitude at slow speed as she pivots from the回眸 stance into a low crouch, orange-yellow fire ribbons beginning to swirl around her feet and embers spiraling upward past her shoulders. [Shot 2] At 00:04.500, the camera cuts to a wider shot of the full desktop as she explodes out of the crouch into a dramatic backbend spin — one leg planted, the other extended far to the side-rear, torso twisted and arched backward, ponytail flaring wide in the motion — and roars [Japanese] 超必殺・忍蜂！ A ring of glowing shuriken erupts from her spinning body and orbits outward like a whirlpool across the center of the screen; as the blades sweep through the icon columns, open fans launch from her wrist in rapid succession and strike the icons one by one — each struck icon wobbles violently, peels off its grid position, and tumbles downward with motion blur past the reflective ground out of frame, trailing orange-yellow sparks. The final shuriken detonates at the center of the grid as a white-blue light bloom, shaking the whole desktop loose; every remaining icon rains down in a cascade while her spin finishes in a low landing, one hand extended forward, palm up. [Shot 3] At 00:10.500, the camera cuts to a medium close-up of the young woman across the now-empty center of the screen; her expression stays calm and unbothered, lips pressed into a confident smirk while embers drift past her shoulder. She slowly raises her open fan beside her face and says [Japanese] 花蝶扇。 Orange-yellow flame begins to gather along the fan's ribs like liquid fire pooling on silk, the light reflecting off her white waist knot and red-floral ribbons as tiny sparks orbit her wrist. [Shot 4] At 00:13.500, the shot cuts back to the full desktop as she sweeps the burning fan in a wide graceful arc through another spin; ribbons of orange-yellow flame unfurl from the fan like butterfly wings trailing behind her, and each ribbon's tip hooks one falling icon from below the frame, reeling it smoothly up into its exact original grid position — every lock-in flashing a small white-blue light bloom with a sharp click as the icons seat crisply back into place, restoring both columns perfectly. The last ribbon curls around the final icon and dissolves into sparks that spiral back into her fan as she closes it with a snap at her hip. [Shot 5] At 00:17.000, the camera cuts to a low-angle hero shot as she settles into her classic pose from : side-turned stance with weight on the rear leg, one hand on her waist, the closed fan held elegantly beside her face, chin tilted down in a cold confident glare while her ribbons and hair flare outward in the residual wind. The camera pulls out with small amplitude at slow speed, revealing the fully restored desktop around her; drifting orange sparks fade to black as she holds the pose until the end of the video. overall_soundscape: Low flame crackle builds under a rumbling charge, then an explosive whoosh on the backbend spin — rapid shuriken whistles and fan-snap cracks striking icons one after another — followed by cascading rattling clatters as icons tumble out of frame and a sharp white-blue burst pop. A crisp fan snap and a soft confident breath carry across the empty desktop during the calm close-up. Rising flame hiss gathers along the fan's ribs, then graceful silk-ribbon whooshes sweep through the spin while crisp snap-back clicks land one after another as each icon locks into place with tiny light-bloom pops, ending with a low resonant boom under guttering ember crackle. non_diegetic_music: Driving taiko drums with fast electronic percussion at a high tempo building to a hard hit on the shuriken barrage, dropping out to sparse sustained synth and a single koto pluck during the calm close-up, then returning for one final strong downbeat as she locks her classic pose. ---](https://image.24vids.com/tw-2102662408271692102/amplify_video_thumb/2102645570531897344/img/l-JpLtftZ8cSjK6E.jpg)
 knowing smile as she lowers her wine glass. The giant replay screen behind her flashes blinding white. Hard cut to black. A single heartbeat sound. The replay screen bursts to life — but instead of football highlights, it shows intimate, hidden footage: the football champion @[Image 4](image_4) and the elegant dark-haired brunette @[Image 2](image_2) in a passionate embrace in a private locker room, his winner’s medal still around his neck. The crowd in the ballroom gasps audibly. 5–12s | Consequence Cut to the blonde woman @[Image 3](image_3) at the elegant table. Her face drains of color as she stares at the massive screen. Tears well up again. She picks up her engagement ring from the table in her bare hand and clutches it so tightly it digs into her right hand. The football champion @[Image 4](image_4)(still in black suit, medal now missing from his neck) stands frozen a few feet away, horror dawning on his face. He (medal now missing from his neck) turns toward the screen, then desperately toward the blonde. Blonde woman (whispering, broken): “You said it was only the match that changed everything…” The blonde @[Image 2](image_2) walks away abruptly, knocking over a champagne flute. It shatters loudly on the marble floor — the sound cutting through the now-hushed ballroom. She looks between the champion @[Image 3](image_3) and the brunette @[Image 1](image_1), betrayal turning to cold fury. Blonde woman @[Image 2](image_2)(voice cracking but gaining strength): “Then why does the final replay show you celebrating with her… while I waited for you?” The replay screen loops the damning embrace in slow motion. Guests murmur and film with their phones. 27–30s | Next Cliffhanger The brunette @[Image 1](image_1) smiles wider, turns, and begins walking away through the crowd as the replay screen suddenly cuts to new unseen footage — a close-up of the brunette @[Image 1](image_1) slipping something into the champion’s drink earlier that night, followed by a quick flash of a mysterious document with official-looking seals. The champion’s face twists in shock and realization. The blonde’s eyes widen in horror as she sees it too. Freeze frame on the three of them — triangle of tension. Text on screen fades in: EPISODE TWO Fade to black. Distant crowd applause mixes with a rising, ominous orchestral sting.](https://image.24vids.com/tw-2079099388471992773/amplify_video_thumb/2079097343341961216/img/KbmIB9mujj0Sd6Tt.jpg)
![She doesn’t play tennis. She hunts points. Every cut hits like a winner. Made with Seedance 2.5 on Fish Creative Try it for free 👇 Prompt: STEP 05 - SEEDANCE 2.5 GENERATION SEEDANCE 2.5 STORYBOARD AS REFERENCE FAST CUT 24FPS HANDHELD THROUGHOUT AESTHETIC: Cinematic sports reel, 20 seconds, 16:9. Natural light, highlight halation. Handheld micro-tremor, never gimbal. Fast cuts every 0.8-1.5s. Motion blur 24fps, 35mm grain. Fixed midday light all 20 seconds: overhead sun, hard short shadows. CHARACTER: Young athletic woman from REFERENCE IMAGE. Dark brown hair in high ponytail with loose strands, white Nike visor, navy Nike racerback tank with white swoosh, navy pleated tennis skirt with white swoosh, white wristband, fine gold chain with small cross, holding tennis racket. USE REFERENCE IMAGE FOR FACE AND EXACT WARDROBE. Same outfit every single shot. Do not change colors, logos, hair, or jewelry. LOCATION: Outdoor tennis court. Blue cobalt inside, green outside, white lines. Black fence, empty bleachers. Midday sun. [0:00-0:01] Extreme close-up top-down. White sneakers and navy skirt hem frame the racket. She spins the racket two rotations from the handle on the blue court. [0:01-0:02] Close-up face from reference image — eyes bright, half smile, one hand on visor, tosses yellow ball in air, slight dolly-out. [0:02-0:03] Match cut on ball to overhead top-down. She completes the serve on the baseline. Hard short shadow at her feet. [0:03-0:05] Medium handheld counter-direction. Violent forehand drive, torso rotating, navy tank twisting, racket cutting air. [0:05-0:06] Low angle dutch tilt. Running parallel to the net in navy skirt, forehand with motion blur. [0:06-0:07] Full shot. Jumping to smash overhead against the sky, ponytail and visor catching sun. [0:07-0:08] Extreme close-up footwork. White sneakers moving fast on blue cobalt court. [0:08-0:09] Medium through net mesh, slow dolly-in, slow motion. Tucks a loose strand behind ear, lowers racket, same face and navy kit from reference. [0:09-0:10] Extreme low angle, backlit sun. Serves in slow motion from behind, silhouette of visor, tank, and skirt against sky. [0:10-0:11] Wide from blurred bleachers. Small figure hitting crosscourt backhand. [0:11-0:12] Reverse medium handheld other side of the net. Two-handed backhand, weight back, navy outfit identical to reference. [0:12-0:13] Wide from bleachers. Small figure forehand drive. [0:13-0:15] Medium handheld counter-direction. Violent forehand drive closing the point. [0:15-0:17] Hero close-up. Same face as reference image, slight smile, hand near visor, midday sun, navy Nike kit. [0:17-0:20] Extreme low angle through racket strings. Face from reference behind the strings. Bounces yellow ball twice, brings ball toward lens until it fills the frame. AUDIO: No dialogue. Diegetic sound only — ball impact, sneaker squeak, breathing, ball bounce, palm wind, fence vibration. No music in engine.](https://image.24vids.com/tw-2094944675044245596/amplify_video_thumb/2094943411141054464/img/xgk6PAjmkXybQiEc.jpg)
![U-Net by hand ✍️ ~ 17 steps walkthrough below I consider U-Net as a key milestone in deep learning, the first image-to-image model that really worked! It came out of medical imaging, an unusual place, not from NeurIPS or CVPR or ACL. Now it is the backbone of diffusion models, which you see in almost all modern image generation models. I drew the network as a C so the matrix multiplication flows naturally down. Tilt your head to the right and it is a U again. 🤣 Goal: push a 3 x 16 image down to a 2 x 4 bottleneck and back out again, filling in every cell yourself. = 1. Given = An image of three channels, R, G and B, sixteen pixels wide, and every kernel the network will use. = 2. Convolution 1 = Let us slide the first kernel over the image. Each output is one multiply-and-add over a 2 x 3 window, and the result is the green feature map. = 3. Find the maxima = We circle the largest value in each 1 x 2 window. Circling first is worth the extra step: it is the pooling decision, made before anything is written down. = 4. Max pool 1 = Let us copy those maxima down. Sixteen columns become eight, and half the detail is gone for good. = 5. Convolution 2 = We convolve again with the second kernel, deeper into the contracting path. The feature map is blue now. = 6. Find the maxima again = Same move as step 3, on the blue map. = 7. Max pool 2 = Eight columns become four. = 8. The bottleneck = Let us convolve once more. This is the bottom of the U, a 2 x 4 block that is everything the network kept. = 9. Spread it out = We start back up. The transposed convolution writes each bottleneck value into a wider grid, leaving gaps between them. = 10. Transposed convolution 1 = Let us fill those gaps by convolving over the spread-out grid. Four columns become eight. = 11. The first skip = We copy the encoder's matching row straight across. This is the skip connection, and it is the whole reason a U-Net can recover detail that pooling threw away. = 12. Convolution with the skip = Let us convolve the upsampled features together with the copied ones. = 13. Spread it out again = Same as step 9, one level up. = 14. Transposed convolution 2 = Eight columns become sixteen, back to the width we started at. = 15. The second skip = The encoder's first feature map comes across, the one made before any pooling happened. = 16. Convolution and ReLU = We convolve, then cross out every negative and set it to zero. = 17. Output convolution = Let us apply the last kernel. Out comes R', G' and B', an image the same size as the one we started with. The outputs: R' = [3, 0, 7, 0, 7, 0, 17, 0, 3, 0, 9, 0, 2, 0, 6, 0] G' = [1, 20, 1, 10, 1, 12, 1, 19, 2, 5, 1, 11, 1, 3, 1, 7] B' = [4, 20, 8, 10, 8, 12, 18, 19, 5, 5, 10, 11, 3, 3, 7, 7] Congrats! You just calculated a U-Net by hand. 💾 Save this post!](https://image.24vids.com/tw-2081382845243691256/ext_tw_video_thumb/2081382802667249664/pu/img/n2gZcnKRYe9G781o.jpg)
![一番最後の[Prompt for original image]の部分に画像生成に使用したPromptを入れると一貫性が増します。不要な場合は3行削ってしまっても大丈夫です。 --- Extreme wide-angle perspective and dynamic pose remix edit. This is an EDIT of the original image, not a new character. Use the original image as a strict reference for: – the person’s identity, hairstyle, and overall fashion style, – the general type of background and location (same street, same room, same beach, same kind of architecture, etc.). You are allowed to completely change the camera position, angle, and pose, but you must keep the scene in the SAME location and keep the SAME person and outfit design. Camera and perspective: – Use an ultra wide-angle or fisheye feeling lens (around 12–18mm full-frame look). – The camera angle MUST change significantly from the original: use dramatic angles such as • worm’s-eye view from directly below looking up, • bird’s-eye view from directly above looking down, • very low angle from the ground, • high angle from above, • tilted Dutch angles. – Always create strong foreshortening: body parts close to the lens look huge, while the rest of the body falls away in perspective. – The final result must look like a bold fashion or street photo, fully photorealistic, not illustration or anime. Background consistency: – Keep the same location as the original image: same street, same bridge, same room, same studio, same beach, same general structures and materials. – Do NOT replace the background with a completely different place. – Because the camera angle changes, it is allowed and expected that different parts of the environment become visible. – When new areas appear, extend the original environment logically (same buildings, fences, road markings, walls, colors, materials, lighting style), as if the camera moved within the same place. Body parts near the lens (1–2 parts, sometimes 3): – In each edit, choose ONE or TWO main body parts to be extremely close to the lens (sometimes even THREE in more complex poses). – Vary them from image to image, do NOT always use the same body part. – Allowed near-the-lens parts include: • one or both hands / fingers reaching toward the camera, • one or both feet / shoes / boots near the lens, • knees or thighs, • face very close to the lens, • shoulders or chest close to the lens in a leaning pose. – The chosen body parts should come extremely close to the lens, almost touching it, with visible skin texture, fabric texture, and realistic wide-angle distortion. Pose and overall body (complex and varied): – Create strong, cool, dynamic poses that match the extreme perspective. – Randomly use different pose types, including: • standing with one leg or one arm reaching toward the camera, • crouching or squatting low to the ground, • sitting on the floor or on objects, • lying on the ground with legs or feet toward the lens, • leaning forward aggressively toward the camera, • twisting the body, crossing legs, or arching the back for more dynamic lines. – Allow complex poses where: • both hands are near the lens forming shapes (peace signs, triangles, frames, pointing toward the viewer), • both feet are toward the lens, • one hand and one foot are both large in the foreground, • the face is close to the lens while hands or feet are also visible in perspective. – Maintain believable anatomy even with extreme foreshortening. Angle and attitude (randomized): – Randomize camera angle and orientation (up, down, side, Dutch tilt) while keeping the composition visually balanced and powerful. – Keep the vibe cool, confident, and fashion/editorial or street style, depending on the original outfit. – Facial expressions can vary (serious, playful, confident, mysterious), but must still look like the same person. Lighting and rendering: – Keep the general time of day and lighting mood similar to the original (night vs day, indoor vs outdoor, soft vs hard light), but you may enhance contrast and color to make the image punchy and dramatic. – Maintain realistic shadows and contact points with the ground or floor. – High-resolution, sharp details with clear skin texture, fabric weave, and material highlights. Variation and randomness: – Each edit should look noticeably different from the original image and from other edits, with different: • camera angles, • pose types, • which body parts are closest to the lens, • orientation (straight, tilted, from above, from below). – Avoid repeating the exact same single-foot-close-up composition; produce a wide variety of dynamic poses and angles. Strict rules: – Do NOT change the person into someone else. – Do NOT change the outfit type; only restyle it through pose, perspective, and small natural movement of clothing. – Do NOT move the scene to a completely different location; always stay in a plausible extension of the original place. – Do NOT add text, logos, watermarks, or graphic design elements. – Do NOT switch to painting, illustration, or anime style; keep it photorealistic. Overall: Transform the original photo into a dramatic, photorealistic, ultra wide-angle shot with an extreme camera angle (including views from directly below or above), where one or more body parts are right next to the lens and look huge, the rest of the body recedes in perspective, and the same person strikes a stylish, complex, powerful pose in a consistent, expanded version of the original environment. Also, below is the prompt for generating the original image. Please use it as a reference. [Prompt for original image] #nanobanana2](https://image.24vids.com/tw-1997138129225241083/amplify_video_thumb/1997137979635326976/img/SgrkcWn97sIXcOyy.jpg)
