POV: Day Three at the Mondstadt Adventurers' Guild Front Desk — AI Video from Neta Studio
Final Video: POV: Day Three at the Mondstadt Adventurers' Guild Front Desk
POV: Day Three at the Mondstadt Adventurers' Guild Front Desk drops you into a first-person morning inside 提瓦特大陆 (Teyvat): you are the guild clerk behind the reception counter in Mondstadt, and it is day three. All you want is to stamp twelve parchment commission slips. The wind — the famously opinionated wind of the City of Freedom — wants something else entirely.
The video is a 15-second live-action found-footage sequence shot entirely in first person: five hard-cut POV shots that move from the first gust tearing the paperwork off the counter, to the heavy brass stamp rocking and rolling off the stack, to a last slip sailing out through the arched stone window toward the green windmill. No faces, no third-person shots — only hands, sleeves, ink, dandelion seeds and the world's wind doing what it does best.
Watch it now: POV: Day Three at the Mondstadt Adventurers' Guild Front Desk →
The Video
9:16 vertical · 15 seconds — rendered with Seedance 2.0 Fast (image-to-video) from the world's own reference frame, in a single pass.
How It Was Made
Production Process Breakdown
The world starts from a single Chinese sentence — “帮我生成一个 原神世界观 忠于原著” (help me build a Genshin world, faithful to the source). Neta Studio expands it into 提瓦特大陆 (Teyvat): seven archons, seven nations, the Traveler, Paimon, Venti, Zhongli and the Raiden Shogun — plus the events and secrets that shape the world: the Archon War, the Cataclysm of Khaenri'ah, the World Tree and forbidden knowledge. Everything locks to one visual system: Genshin Impact official anime fantasy, cel shaded, vibrant elemental landscapes.
A photorealistic scene reference is generated first: the guild front-desk clerk's own two hands and forearms over the worn wooden counter — rolled-up off-white linen sleeves, the pale-blue wind-crest badge at the wrist, the heavy brass ink stamp, the windmill turning over the lake outside the arched window. This single frame becomes the atmosphere and prop bible for the video: counter layout, sleeve and badge design, material texture and world identity.
A creator-style 9:16 pitch board is made first — “THE WIND ATE MY PAPERWORK”, three overlapping POV frames with handwritten captions (“ONE GUST, TWELVE SLIPS GONE”). The first draft is regenerated with a stricter camera rule: every frame must stay strict first-person POV, nothing above the forearm, no external camera angle. The final board locks the shot plan for all five cuts.
The 15-second video is rendered in a single pass with Seedance 2.0 Fast: five hard-cut first-person shots, from the first gust over the counter to the last slip sailing out the window — with raw location sound and a tired, dry, sarcastic Chinese voiceover from the clerk. The finished MP4 publishes instantly to a shareable link that plays in any browser, no download required.
Generation Prompt
“9:16 vertical 15-second realistic live-action first-person POV smartphone video, raw handheld footage, natural morning window light, slight motion blur, obvious HARD CUTS between different first-person angles, no on-screen text, no captions, no subtitles, no readable writing, no watermark. ABSOLUTE CAMERA RULE: the entire video must remain first-person POV at the camera wearer's own eye level. Do not show the character's face, head, hair, shoulder, torso, back, full body, or any third-person view. Only hands, forearms, rolled-up off-white linen sleeves with a dark blue tabard edge and a pale-blue wind-crest cloth badge at the wrist, plus tools, objects and the environment. Use the provided reference image only to lock atmosphere, counter layout, sleeve and badge design, material texture and world identity. Do not treat it as a single continuous shot. The final video must contain obvious hard cuts and different first-person angles. CORE INTERACTION OBJECT: a heavy dark-wood-and-brass ink stamp. It sits on the wooden reception counter and is the only object heavy enough to pin loose parchment slips down. The POV character grabs it and drops it onto the stack as a paperweight. It fails by rocking, then rolling off the stack, knocking over a clay ink pot and releasing the papers it was holding. This object is the center of the scene, not background decoration. Story: a guild front-desk clerk in a lakeside city of wind just wants to stamp twelve parchment commission slips, but repeated spiral gusts through the open stone windows tear the paperwork off the counter, and the last slip sails out the window. Setting and atmosphere: a tall stone-and-timber guild hall, worn wooden reception counter, arched stone windows open to warm morning light, wooden rafters overhead, a hanging cloth banner with a stylized pale wing emblem, a green windmill turning over a blue lake outside, drifting dandelion seeds. Low-saturation naturalistic color, real dust in the light, not glossy, not oil painting, not anime, not cel-shaded, not a cinematic poster, no fantasy magic effects beyond visible moving air and flying paper. Attention pulse requirement: every short segment must contain an attention pulse or immediate visual payoff. Do not save all danger or surprise for the final seconds. Each pulse is causally tied to the same wind-versus-paperwork event: paper hitting the lens, tool failure, ink spilling, arms lurching, camera snapping up. Shot 1, 0-2.5s, FIRST-PERSON LOOK-DOWN POV over the counter: the gust is already happening at the very first frame. A dozen parchment slips lift and spin off the stack, one flapping sheet smacks the edge of the lens and slides away, dandelion seeds whirl past. The clerk's right hand slams flat onto the remaining stack a moment too late; the camera jolts down with the arm. Shot 2, 2.5-5.5s, FIRST-PERSON TOOL INTERACTION MACRO POV: Hard cut. Close on the counter surface. The hand enters from the bottom right, picks up the heavy brass ink stamp, and sets it down hard onto the surviving stack with a solid thud. The parchment flattens under it. The air goes briefly still; only a corner of one slip trembles. Shot 3, 5.5-8.5s, FIRST-PERSON LOOK-DOWN POV, tighter: Hard cut. A second gust curls under the stack from the open window. The brass stamp rocks, tips, and rolls across the counter on its side, striking a small clay ink pot; dark ink runs out across a parchment slip. The hand jerks back from the spill; the camera flinches with it. Shot 4, 8.5-11.5s, FIRST-PERSON ARMS-WIDE GRABBING POV: Hard cut. Both forearms sweep out across the counter and into the air chasing flying slips, hands clapping shut on one sheet mid-flight while two more escape past the lens. The camera lurches sideways with the reach, framing briefly lost, focus hunting. Shot 5, 11.5-15s, FIRST-PERSON SNAP-UP POV: Hard cut. The camera snaps upward toward the rafters: parchment slips drifting high near the wooden beams and the hanging winged banner. One slip sails cleanly out through the tall arched stone window toward the distant green windmill. The hand lowers out of frame. The camera holds, still. Audio: no music bed. Raw location sound: gusting wind through stone arches, parchment flapping and scraping, the solid thud and rolling knock of the brass stamp, the clay ink pot tipping, boots shifting on a wooden floor, breathing. Include a tired, dry, sarcastic first-person Chinese voiceover from the clerk, spoken like live handheld footage, not clean narration, broken into short phrases with natural pauses. Do not speak continuously; leave room for the wind, paper and object sounds. Voiceover text timed across 15 seconds: (silence over wind for the first two seconds) 来协会前台第三天... 没人告诉我这儿的风有自己的主张。 (pause, stamp thud) 我只要盖十二张单子。十二张。 (pause, paper flapping, ink spilling) 又来—— (pause, then flat) ...那张是奖励结算单。 Tone: worn-down irritation. A grounded life-slice problem in a windy lakeside city, not a heroic trailer. Do not make it a single continuous shot, do not show any part of the body above the forearm, do not add unrelated creatures or magic effects.”
Model: Seedance 2.0 Fast — image-to-video, single pass, 15s @ 9:16 vertical.
Asset Prompts
“Scene reference photograph for a first-person POV short video, shot on a handheld smartphone. Point of view: a young front-desk clerk standing behind a wooden adventurers' guild reception counter inside a tall stone-and-timber hall in a lakeside fantasy city of wind. Visible in frame from the camera wearer's own eyes: their own two hands and forearms in rolled-up off-white linen sleeves with a dark blue tabard sleeve edge, a small pale-blue wind-crest cloth badge pinned at the wrist cuff, one hand holding a heavy brass ink stamp, the other pressing down a loose stack of parchment commission slips on the counter. On the counter: an open leather ledger, a tin tray of scattered parchment slips, a spilled dandelion seed or two, a clay ink pot, a wooden request board behind with pinned notes fluttering. Background: arched stone windows with warm morning light, tall wooden rafters, a hanging banner of a knightly order with a stylized wing emblem, a glimpse through the window of a green windmill turning against a blue sky over a lake. Style: cinematic photorealistic, live-action found-footage aesthetic, realistic human skin and fabric texture, realistic morning window light, slight lens haze, grounded realism, not anime, not illustrated, not cel-shaded, not painterly. No text, no captions, no watermark, no readable writing anywhere.”
“Vertical 9:16 cinematic video pitch board with a polished, creator-made collage layout. Use cinematic photorealistic live-action found-footage aesthetic, realistic human skin and fabric texture, warm realistic morning window light, grounded realism (not anime, not illustrated, not cel-shaded) consistently across all cinematic frames. Add restrained handwritten graphic elements that support the visual hierarchy. CRITICAL VIEWPOINT RULE for all three cinematic frames: every frame is strict first-person POV filmed from the camera wearer's own eye level, as if a phone is held at their face. Only their own hands, forearms and rolled-up off-white linen sleeves with a dark blue tabard edge and a pale-blue wind-crest cloth badge at the wrist may appear, entering frame from the bottom or bottom-right. Absolutely do not show the person's head, face, profile, cheek, ear, hair, shoulder, chest, torso, back, or any part of their body above the forearm. No over-the-shoulder view, no mirror, no external camera angle, no second person visible. Top information area: Large handwritten hook title with expressive brush-pen lettering: "THE WIND ATE MY PAPERWORK". Place a clearly legible location block beneath the title: "LOCATION · MONDSTADT ADVENTURERS GUILD" and beneath it "BUSY MONDAY MORNING". Main visual area: exactly three overlapping cinematic frames with varied scale, slight rotation, clean edges, clear hierarchy. Each caption sits directly on the lower border of its own frame, matching that frame's content. LARGEST frame, upper portion of the board, roughly half the board area: strict first-person POV looking down and forward across a worn wooden guild reception counter in a tall stone-and-timber hall. The clerk's own two hands enter from the bottom of frame, one slamming flat onto a stack of parchment commission slips, as a sudden spiral gust rips a dozen slips upward off the counter, papers tumbling and spinning mid-flight through slanted morning light, dandelion seeds swirling with them, a brass ink stamp knocked over and rolling. Visible behind: arched stone windows, wooden rafters, a hanging knightly-order banner with a stylized wing emblem, a green windmill turning over a blue lake outside. Its caption: "ONE GUST, TWELVE SLIPS GONE". SMALLER supporting frame, middle right, overlapping the largest frame's lower edge: strict first-person POV macro look straight down at the counter surface, nothing but hands and desk in frame: a single parchment commission slip pinned under the clerk's thumb, its lower half already curling and lifting on its own in a visible ripple of moving air, a faint pale-teal swirl of wind curling around the brass stamp beside it, tiny dandelion seeds stuck to wet ink. Its caption: "THE INK IS STILL WET". SMALLER anticipation frame, bottom of the board: strict first-person POV snapped upward toward the ceiling of the guild hall, no hands in frame: loose parchment slips drifting high among tall wooden rafters and the hanging winged banner, one slip sailing out through a tall arched stone window toward the distant green windmill and blue lake. Its caption: "THAT ONE'S GOING OUTSIDE". Give every frame distinct story information: the central event, the visual style, the tired-annoyed emotional direction, the distinctive stone-arch-and-windmill identity of Mondstadt, and the world's wind rule are immediately clear. Add at most one restrained handwritten accent: a small hand-drawn spiral-wind arrow curving off the largest frame's flying papers. Omit frame-role labels, frame numbers, numeric timestamps, editing timecodes, timeline overlays, app UI, engagement icons, progress bars, CTA buttons, watermarks, and logos. Render every displayed title, location name, time label, and action caption with correct spelling and crisp legibility.”
“Vertical 9:16 cinematic video pitch board with a polished, creator-made collage layout. Use cinematic photorealistic live-action found-footage aesthetic, realistic human skin and fabric texture, warm realistic morning window light, grounded realism (not anime, not illustrated, not cel-shaded) consistently across all cinematic frames. Add restrained handwritten graphic elements that support the visual hierarchy. Top information area: Large handwritten hook title with expressive brush-pen lettering: "THE WIND ATE MY PAPERWORK". Place a clearly legible location block beneath the title: "LOCATION · MONDSTADT ADVENTURERS GUILD" and beneath it "BUSY MONDAY MORNING". Main visual area: Arrange exactly three overlapping cinematic frames with varied scale, slight rotation, clean edges, and clear visual hierarchy. Give the largest frame the most space. Keep hands, central actions, and important location details unobstructed. Largest cinematic frame: strict first-person POV from a guild front-desk clerk's own eyes, looking down at a worn wooden reception counter in a tall stone-and-timber hall. Their own two hands in rolled-up off-white linen sleeves with a dark blue tabard edge and a pale-blue wind-crest cloth badge at the wrist: one hand slams flat onto a stack of parchment commission slips while a sudden spiral gust of air rips a dozen slips upward off the counter, papers tumbling and spinning mid-flight through slanted morning light, dandelion seeds swirling with them, a brass ink stamp knocked over and rolling. Add one small legible action caption partly on its lower border: "ONE GUST, TWELVE SLIPS GONE". Supporting cinematic frame: strict first-person POV macro look-down at the counter surface: a single parchment commission slip pinned under the clerk's thumb, its lower half already curling and lifting on its own in a visible ripple of moving air, a faint pale-teal swirl of wind curling around the brass stamp beside it, tiny dandelion seeds stuck to wet ink. Add one small legible action caption partly on its lower border: "THE INK IS STILL WET". Anticipation cinematic frame: strict first-person POV snapping up and across the guild hall: loose parchment slips drifting high among tall wooden rafters and a hanging knightly-order banner with a stylized wing emblem, an arched stone window open to a green windmill turning over a blue lake, one slip sailing straight out the window. Add one small legible action caption partly on its lower border: "THAT ONE'S GOING OUTSIDE". All three cinematic frames must remain strict first-person POV; do not show the viewpoint character's face, back, full body, over-the-shoulder view, or any external camera angle. Give every frame distinct story information: the central event, the visual style, the tired-annoyed emotional direction, the distinctive stone-arch-and-windmill identity of Mondstadt, and the world's wind rule are immediately clear. Add at most one restrained handwritten accent: a small hand-drawn spiral-wind arrow curving off the largest frame's flying papers. Omit frame-role labels, frame numbers, numeric timestamps, editing timecodes, timeline overlays, app UI, engagement icons, progress bars, CTA buttons, watermarks, and logos. Render every displayed title, location name, time label, and action caption with correct spelling and crisp legibility.”
Reference Frames
Why Choose Neta Studio
Professional — The cloud harness supports the full workflow from world building to cinematic video, all running in the cloud with no local setup. Stable access to the latest models: Claude Opus 5 · GPT Image 2 · Seedance 2.0 Fast
One-click generation — Officially tuned skills drive every step: world building, key art, reference frames, video generation, and instant publishing to a shareable link.
Community & IP-first — Adapt any world or start fresh from a single sentence. Keep your frames, prompts and sprites — remix them into new videos anytime.
Studio Interior
Start Creating
This video was generated by Neta Studio AI from a single sentence. The world took minutes. The video took minutes. You can do it too — adapt this world or start fresh from any IP. No coding required, free to start.