Culture & ArtsMusic Video
An old man's memories in a tavern tie together a farm boy's experiences, the hardships of life and his dreams of the jianghu, telling a down-to-earth “Youth's Journey.”
01 / Background
“Youth's Journey” is a song with lyrics and music by Xiao Shaoyan, and the film tells a memory: in a tavern, an old man with a white beard talks about the ambitions of his youth, and the story moves back and forth between fields, market streets, shops and the jianghu. The young man is from a farming family, with the marks of hard living on his clothes and face, so his story feels concrete from the very start.
Over a four-minute song, the images had to keep pace with the lyrics line by line while also holding the whole memory together. The film uses the warm-toned tavern as the place where the story is told, cutting into the youth scenes from the pouring of wine, the raising of a cup and the old man's expressions, and returning to the table again and again. The setbacks of the outside world thus become one man's lifetime of experience, rather than a pile of unrelated period scenes.
The on-screen lyrics help tell the story too. Small text follows the lyrics, large red calligraphy picks out the emotionally charged words, and toward the end some characters grow larger and turn white. Close-ups of people, wide shots of city gates and the size of the text work together to set the weight of each moment, so the passages where the old man speaks quietly and the grand jianghu passages move at visibly different paces.
02 / Creative Highlights
The character brief stresses a farm child with rough skin and the marks of time. The film tells the young man's story through actions like studying, lingering in the fields, packing his bags and picking fruit, while the old man's wrinkles, his drinking and his smile make it clear that a long time has passed.
After each section, whether he leaves home, goes into business or meets with cold treatment, the film cuts back to the warm golden tavern. Similar lighting, the same tabletop and close-ups of people tell viewers the story is still being told here, and set the ups and downs of the outside world against the old man's present calm.
In this street shot, the whole frame turns black and white: the street is full of people in dark clothes, and only the young man in white walks down the middle, before the next shot cuts to large red characters. Color separates the individual from the crowd, so the tension between going along with everyone and staying true to himself is clear without any explanation.
Shots alternating between the old man and a child, father and son reading together, and pointing into the distance across the fields are the gentle passages of the story; drum troupes, sails, landscapes and clashes then widen the scale. The film ends back with the old man drinking, rising to leave and his figure receding into the distance, leaving a lingering note after all the excitement.
03 / Scene Breakdown
In a warmly lit tavern, an old man with a white beard pours wine, raises his cup and begins to tell of his youth. An opera-stage hero, old books and a young man with a blade appear one after another, showing what kind of person he wanted to be as a boy.
Golden light streams through the lattice windows, guests sit in a circle with their backs to the camera, and the title characters float up from the center of the frame. The place where the story is told comes first.
The old man's hand pours wine into a cup, then the shot pushes in to his downcast face. One cup of wine and one expression set the tone of the memory.
A general in a red robe and gold crown glares as he strikes a pose, then a finger runs across an old book and a father and son lean in to read together. What he learned as a child about “being a good person” all came from images like these.
The young man charges into a crowd with a blade, and in the next shot the whole frame turns black and white: in a street full of people in dark clothes, only he is dressed in white.
His father points to the fields outside the door and tells him to farm for a few years first; he thinks it over through a moonlit night, crosses the mountains and arrives at the city gate. He buys a load of fruit, a snowfall freezes the whole lot, and the shopkeeper refuses to take responsibility.
Father and son stand side by side in front of an old house by the fields; the father turns to call him over, then raises his hand to point at the paddy fields under the setting sun.
A lone figure walks through misty mountains, then stands on a summit looking down at the sea of clouds below.
He stands with his back to the camera before a huge city gate and a surging crowd. Pulling out from one face to an entire city makes the outside world feel especially vast.
Baskets full of fruit give way to him sitting stunned in heavy snow, the fruit on the ground frozen and spoiled. His first business venture ends in a loss.
He walks into a shop and confronts the owner with an orange in hand; the shopkeeper in a purple robe stays expressionless, while his face darkens in the shadows.
The image returns to the tavern table, where the old man raises one finger in the light at the door, and large red characters press down on the frame.
He gets into a wealthy household through connections but is left out in the cold, works for relatives without getting paid, and the shop he opened with a good friend falls apart. In middle age, he passes the same lessons on to his own child, then sends the child out into the world.
The steward weighs the bundle his parents sent; at a banquet, a roomful of people raise toasts while he cleans up alone in the mansion.
An accountant flips through a ledger, followed by an empty desk and drifting smoke; a little shop with fully stocked shelves becomes, in an instant, an empty storefront gathering dust.
Two men seen from behind with arms over each other's shoulders, in an instant face off in the snow, then a cut back to the old man drinking from his cup. The falling-out between friends is passed over in a single stroke.
A child grins at the camera, runs along a flagstone path, then leans in to read with his father. The warm-lit images suddenly ease the pace.
The father pats his child's head and points to the rice fields at sunset, followed by an ox standing in a paddy. It mirrors the earlier shot of his own father pointing to the fields.
The old man sits back at the table and gestures with his hand as large white and red characters press down on the frame together, and the talk turns to the ways of the world.
The county magistrate guards chests of gold and silver, the fields are flooded, constables come to the door shoving and demanding money; gossip spreads through the village, and a bully swaggers down the street. The shots in this section come fast and dense.
An official in brocade robes smiles over his treasure, followed by flooded fields and constables storming into a wheat field.
Constables and farmers grapple with each other, an officer holds out his hand for money with a piece of silver in his palm, and he sits dazed by the roadside.
People on the street gather to gossip and stand in a row under dark clouds, an old man points at him, and a bare-chested brute leads his men through the market.
A burly man in a yellow robe grins in front of a line of soldiers, ending on an extreme close-up of rotten teeth.
The scale suddenly widens: a cavalry charge, thundering gongs and drums, a river full of warships, qinggong duels and a sect in the mountains. After all the excitement, the film returns to the old man fanning himself in the tavern.
Cavalry charge under red flags, followed by a river valley after battle, then drummers beating with all their might amid a screen full of red fragments.
Red-sailed warships crowd the river, a figure stands before the cresting waves, then a face that is half human, half demon mask.
Two figures leap and trade blows in the mist, then blades clash, and finally a mountain gate in the clouds with a long procession. Large red characters appear in step with the action.
Figures in the smoky tavern, then the old man raising a folding fan to cover half his face.
The old man holds his last cup of wine and says he only tells the truth when he's drunk. The characters from earlier then flash back rapidly in black and white as large white calligraphy presses onto the frame character by character. Finally he rises on his staff and walks into the cloud-wrapped mountains.
Holding a steaming cup in both hands, the old man closes his eyes, then turns to gaze at the light outside the window, and turns back with a hearty laugh.
The child reading, the young man before the mountains and the white-robed figure in the crowd flash past one by one, each overlaid with one or two large white characters.
Fighting, slumping down by the roadside, being surrounded by people, and finally a close-up of a pair of eyes, with red characters landing on the key word.
Gripping his wooden staff, the old man walks toward the light at the tavern door and looks back once.
After the large red characters, the white-robed old man walks away toward the distant mountains, and the film ends here.
04 / Storyboards & Final Frames
The whole film follows the lyrics with one keyframe per line, 118 in total. Here they are split into 8 chapters in the film's order, with every two neighboring lines grouped together; the black-and-white flashbacks at the end reuse earlier shots and have no keyframes of their own.
Shot 1.1
Warm light streams through the lattice windows and guests sit together in the smoke; the whole film starts its story here.
Shot 1.2
First the old man in profile, then a push in to a close-up of his face; his white hair and golden rim light show that he has grown old.
Shot 1.3
A deeply wrinkled hand pours wine into a small cup, then the old man raises it, and the memory begins with this cup of wine.
Shot 1.4
A first-person view of the cup in hand, then a cut to a close-up of the old man's downcast eyes as the mood sinks.
Shot 1.5
The old man sits cross-legged before a small lamp, the only light left in the room.
Shot 1.6
A carefree figure walks into a courtyard from behind, and the next image shows only the empty courtyard: the days of youth are gone.
Shot 1.7
An opera from his childhood: a general in a red robe and gold crown strikes a pose on stage, then a push in to a close-up of his face.
Shot 1.8
A finger runs across the illustrations in an old book, followed by a father and son leaning in to read together; how a good person should act was learned from books.
Shot 1.9
The young man charges into a crowd with a blade, and the action and flying dust capture “seeing the world” in the most direct way.
Shot 1.10
In a street full of people in dark clothes, the young man in white walks down the middle; the whole frame is black and white.
Shot 2.1
Father and son stand side by side in front of an old house by the fields, then a cut to the two facing each other: the father has something to say.
Shot 2.2
The father raises his hand to point at the paddy fields under the setting sun, followed by a close-up of a hand plunging into the water among the rice.
Shot 2.3
The young man looks up at the starry sky, then the camera pulls back to a lone figure in the grass under the moon.
Shot 2.4
A figure seen from behind stands among the rice ears in the moonlight, with awns flying up around him.
Shot 2.5
An extreme close-up of his eyes, then he packs his bags under the lamp.
Shot 2.6
A lone figure walks through misty mountains, then stands on a summit gazing at the sea of clouds.
Shot 2.7
After a determined face, he stands with his back to the camera before a towering city gate and a surging crowd.
Shot 3.1
At a roadside fruit stall, he looks over baskets full of fruit and picks them out one by one.
Shot 3.2
He sits stunned in heavy snow as the fruit on the ground freezes and rots.
Shot 3.3
He walks with his back to the camera into a busy shop, then confronts the shopkeeper holding an orange.
Shot 3.4
The shopkeeper in a purple robe stays expressionless, while his face darkens in the shadows.
Shot 3.5
He walks with his head down along a muddy road, and in the next image stands in a barren field looking up at the sky.
Shot 3.6
He stands on high ground looking down over a sea of rooftops, feeling there are opportunities everywhere.
Shot 3.7
The old man talks as he waves a folding fan, and the people at the table listen with smiles.
Shot 3.8
The old man stands in the light at the tavern door, raising one finger.
Shot 4.1
His parents bring silver to plead with the steward, who weighs the bundle with a cold expression.
Shot 4.2
A roomful of people raise toasts, and in the next image he is cleaning up alone in the mansion, ignored by everyone.
Shot 4.3
In a courtyard where grain is drying, people come and go while he crouches to one side working, left out.
Shot 4.4
An accountant sits behind a desk flipping through a ledger, then only an empty desk and drifting smoke remain.
Shot 4.5
A little shop with fully stocked shelves; in the next image it becomes an empty storefront gathering dust.
Shot 4.6
Two men seen from behind with arms over each other's shoulders, then grappling with each other.
Shot 4.7
The old man drinks with his head bowed, and the middle-aged man sits in the tavern.
Shot 4.8
The old man sits chatting with someone across the table and bursts out laughing at this point in the story.
Shot 5.1
The father smiles at his son, then a cut to a close-up of the child grinning.
Shot 5.2
The child runs along a flagstone path, followed by an adult seen from behind walking through a courtyard of fallen leaves.
Shot 5.3
The father holds his child close as they read, pointing to a hero's portrait in the book.
Shot 5.4
On a hillside he points into the distance for his child, then looks down and pats the child's head.
Shot 5.5
He points to the rice fields at sunset, followed by an ox standing in a paddy.
Shot 5.6
The father looks up at the sky; the child, now grown, walks out of the alley with a bag on his back.
Shot 5.7
Back in the tavern, the old man lowers his head in silence, an oil lamp on the table.
Shot 5.8
The old man raises his cup and drinks, then gestures with his hand, ready to talk about what's fair and what isn't.
Shot 6.1
Chests full of gold and silver, followed by an official in brocade robes smiling over his treasure.
Shot 6.2
Flooded fields and houses, with a lone figure standing in the wind at the edge of the fields.
Shot 6.3
Constables storm into a wheat field and shove against the farmers.
Shot 6.4
An officer holds out his hand, and the next image shows a piece of silver in his palm.
Shot 6.5
He sits by the roadside as people on the street gather to gossip.
Shot 6.6
Under dark clouds the crowd stands in a row, and an old man points at him as he speaks.
Shot 6.7
A bare-chested brute leads his men through the market, and he steps up to argue with him.
Shot 6.8
The burly man laughs in the crowd, and the last image is a close-up of rotten teeth.
Shot 7.1
Cavalry charge carrying red flags, followed by a river valley in the smoke after battle.
Shot 7.2
Drummers beat with all their might, red silk flies before the city gate, and crowds fill the square.
Shot 7.3
Red-sailed warships crowd the river; the whole stretch of water is covered in ships.
Shot 7.4
A face that is half human, half demon mask.
Shot 7.5
Two figures leap and trade blows in the mist, followed by a clash of blades.
Shot 7.6
A great hall in the clouds and a long procession, followed by chaos in front of the hall.
Shot 7.7
Figures in the tavern seen from behind, and the old man raising a folding fan to cover half his face.
Shot 7.8
A young man listens, spellbound, as the old man finishes his last words.
Shot 8.1
Holding a warmed cup of wine in both hands, the old man closes his eyes.
Shot 8.2
The old man turns to gaze out of the window, then turns back with a hearty laugh.
Shot 8.3
Gripping his wooden staff, he walks toward the light at the tavern door.
Shot 8.4
The old man looks back once, and the last image is his figure walking into the cloud-wrapped mountains.
05 / Results
We completed a landscape jianghu-themed MV of about 4 minutes, with the original footage in 4K. The lyrics and music were written by Xiao Shaoyan, and the video was made by SD Alchemist Zhongzhong. After release it earned 100K likes, 14K saves and 13K shares on Douyin, and 6M+ views across platforms.
Case Study
A four-minute song about one man's life, from youth to white hair.
Leaving home, doing business, living under another's roof, being betrayed by a friend, watching his child grow up, and finally finishing a cup of wine in a tavern, then rising and walking away.
This is our AI music video for “Youth's Journey,” a song with lyrics and music by Xiao Shaoyan: 118 line-by-line keyframes, turned into video with Kling AI and edited into a 4-minute jianghu ensemble MV.
01
The lyrics of “Youth's Journey” are one long first-person account: one thing after another, with almost every line a new scene.
If each lyric line got its own image, four minutes could easily turn into a pile of unrelated period shots.
First, we gave the whole song a place to tell the story: an old tavern lit from behind. An old man with a white beard sits at a table, pours wine, raises his cup and begins to tell of his youth.
After each chapter of his life, the image cuts back to this table. Viewers always know these are all one man's memories.
A cup of wine and a lowered gaze set the tone of the memory.
02
The first line of the keyframe plan was the character brief: a poor young man, a farmer's son, not a scholar. Good-looking, but with rough skin, wrinkles and small scars.
That brief shaped everything he does: planting rice in the fields, daydreaming in moonlit paddies, crossing mountains with a bundle on his back, picking fruit at a roadside stall.
The same goes for the old man: white hair and beard, deeply wrinkled hands, and the same warm golden backlight throughout. When viewers see his hand pouring wine, they know a long time has passed.
03
We numbered the lyrics line by line following the song's sections, laying them out from the opening to the end, and for each line spelled out who is in the frame, what they're doing, where they are and where the light comes from.
The plan also recorded the director's intent, such as “more shots of fields and oxen,” “the child is especially cute, with very lively eyes” and “cut back to the tavern here.”
The keyframes were made with Midjourney and then handed to Kling AI to generate video. The final film has about 120 shots, averaging one shot per lyric line, so the images follow the singing line by line.
Some shots deliberately echo each other: when he is young, his father points to the fields and tells him to farm for a few years first; later, he uses the same gesture to point them out to his own child. The same action appears twice, and a whole life comes full circle.
04
One line in the plan read: most people are gray; only you are in color.
In the film, this shot turns entirely black and white: a street full of people in dark clothes, with only him in white walking down the middle. No explanation needed; following the crowd versus not following it is right there in the image.
After the young man with a blade, the image turns black and white, and a white-robed figure walks through the middle of the crowd.
The lyric captions have different weights as well: small text follows the singing, while emotionally charged words switch to large red characters. At the end, the characters from earlier flash back rapidly in black and white as large white calligraphy presses onto the frame character by character, running back through his whole life.
The child reading, the young man before the mountains and the white-robed figure in the crowd flash past one after another, each overlaid with large white characters.
05
In the first half, the images are small: a tavern table, a field, a fruit stall, a little shop.
When the story turns to the ways of the world, the shots speed up: the magistrate, the constables, the rumors, the bully, a new character with every line. Further on, cavalry charges, thundering gongs and drums, a river full of warships and qinggong duels push the scale to its largest.
After the most spectacular stretch, the image returns to the tavern. The old man finishes his last cup, rises on his staff, and walks away into the cloud-wrapped mountains.
Ending: after the large red characters, the old man walks away toward the distant mountains.
06
On Douyin the film earned 100K likes, with total views across platforms of 6M+.
For us, what it proves is not how many period scenes AI can draw, but this: Even a long song can be told with AI as one coherent story.
The same hero plays from youth to middle age, the same old man sits from the opening to the end; one tavern holds more than a hundred shots together, and one gesture of pointing to the fields links two generations.
For clients who want an MV or a short story film, this is an approach you can follow: lock the characters first, then lay out the keyframes line by line, and finally use one fixed setting to tie the whole film together.
FAQ
First write the character brief in stone: the young man is a farm boy with rough skin and small scars; the old man has white hair and beard, a deeply wrinkled face and is always in warm golden backlight. Every keyframe prompt carried this description, and the video was generated from the same set of keyframes, so the hero from youth to middle age and the old man from start to finish are always recognizable.
“Youth's Journey” laid out 118 keyframes, one per lyric line, and the final film has about 120 shots, essentially one shot per line. The black-and-white flashbacks at the end reuse earlier images and needed no new keyframes.
The keyframe plan for “Youth's Journey” is dated July 30, 2024, and the final film was completed and released in August 2024.
The final film is a 3840×2160 4K landscape video about 4 minutes long, released on Douyin and other platforms. After release it earned 100K likes, 14K saves and 13K shares on Douyin, and 6M+ views across platforms.
Approach
The keyframes set the characters, actions, settings and reference looks item by item, following the song's sections: the farm boy, the tavern backlit by the window, father and son in the fields and the crowds in the streets recur again and again. In production, Midjourney made the keyframes and Kling AI generated the video, stringing the images for each lyric line into a story that keeps returning to the tavern.
Warm close-ups hold the main storytelling thread steady, while black-and-white streets, cool-toned landscapes and grand city gates mark different emotions; the lyric typography highlights key words, and dissolves and character reactions between the memory shots keep even the long passages flowing.
More Work
Ideal for brand launches · public-sector communications · cultural-tourism campaigns · IP transformation · event openers · earnings visualization · social campaigns · AI workflow development
