Station platform
The woman from image 1 wears the coat from image 2 and walks down the station platform from image 3, then turns to the camera. Tracking shot. Train announcements, footsteps.
HappyHorse 1.1 is at its best when you give it ingredients and tell it how they fit together. This guide shows how to reference images by number, how to direct physics and sound, and 30 prompts to copy.
Write the parts in this order. Each one answers a question the model otherwise guesses.
“The woman from image 1, the jacket from image 2”
“she wears the jacket in the market from image 3”
“walks past the stalls and stops to look”
“walking-pace tracking shot”
“market chatter and footsteps”
Refer to each reference by its position: “the woman from image 1”, “the jacket from image 2”. Upload them in that order. Numbered references remove the guesswork about which picture supplies which element.
One ingredient per image works best. A photo that contains a person, an outfit and a place all at once is harder to reuse than three clean references.
Vague
Use these images to make a nice fashion video.
Directed
The woman from image 1 wears the coat from image 2 and walks down the station platform from image 3, then turns to the camera. Tracking shot. Train announcements, footsteps.
The prompt is where the scene is assembled. Say who holds what, who wears what, and where it happens. Verbs like wears, holds, stands in and walks through tell the model how references relate.
HappyHorse handles weight well, so give it something to move: fabric in the wind, a pour, a swing of a bag, hair when someone turns. One physical detail makes a composite scene feel shot rather than assembled.
Name one or two sounds that fit the setting. Clips run 5 to 15 seconds; keep to one or two actions and extend the clip if you need more time.
Copy a prompt, or open it in AI Video Pro with the engine already selected. Swap the subject for yours and keep the structure.
The woman from image 1 wears the coat from image 2 and walks down the station platform from image 3, then turns to the camera. Tracking shot. Train announcements, footsteps.
The man from image 1 in the suit from image 2 turns slowly on the rooftop from image 3, the jacket catching the wind. Low angle, sunset. Wind and city hum.
The sneakers from image 1 step onto the wet cobblestones from image 2, splashing lightly. Low tracking shot near the ground. Footsteps and drips.
The woman from image 1 wearing the hat from image 2 and the scarf from image 3 walks through the autumn park from image 4, leaves falling. Slow follow. Rustling leaves.
The woman from image 1 twirls in the dress from image 2 in a white studio, fabric flaring out. Camera still, soft studio light. Swish of fabric.
The man from image 1 picks up the bottle from image 2 on the kitchen counter from image 3, reads the label and smiles. Medium shot, morning light. A soft clink.
The headphones from image 1 sit on the desk from image 2; a hand picks them up and puts them on the woman from image 3. Close-up to medium. Soft keyboard clicks.
The basket from image 1 is set down on a blanket in the meadow from image 2; the friends from image 3 open it and share the food. Slow push in. Birds and laughter.
The car from image 1 drives along the coastal road from image 2 at sunset. Aerial follow. Engine hum and waves.
The cup from image 1 is placed on the cafe table from image 2 by the barista from image 3, latte art facing the camera. Close-up. Cafe chatter.
The woman from image 1 and the man from image 2 meet on the bridge from image 3, shake hands and walk off together. Wide shot, golden hour. River sounds.
The drummer from image 1 and the guitarist from image 2 play together in the garage from image 3. Slow orbit. Drums and electric guitar.
The two men from images 1 and 2 play chess on the park table from image 3; one makes a move and the other laughs. Medium shot. Birds and distant traffic.
The two chefs from images 1 and 2 cook side by side in the kitchen from image 3, one tasting the sauce, the other plating. Handheld. Sizzle and clatter.
The hikers from images 1 and 2 reach the summit from image 3 and look out over the valley. Camera rises behind them. Wind.
The dog from image 1 runs across the park from image 2 and jumps up to greet the woman from image 3, who kneels down laughing. Low tracking shot. Barks and leaves.
The cat from image 1 jumps onto the windowsill from image 2 and settles next to the plant from image 3. Camera still. Soft thump and purring.
The rider from image 1 rides the horse from image 2 along the beach from image 3 at a gentle canter. Side tracking shot. Hooves and surf.
The man from image 1 throws the ball from image 2 and the dog from image 3 races after it across the lawn. Wide shot. Barking and wind.
The woman from image 1 walks the dog from image 2 along the misty canal from image 3 at dawn. Slow follow. Footsteps and ducks.
A pastel seaside town at morning, fishing boats returning to the harbor, gulls circling, a baker opening his shop shutters. Slow pan. Waves, gulls, shutter rattle.
A red train winds through snowy mountains, steam trailing, the camera flying alongside. Train rhythm and wind.
A rainy city street at night, neon reflecting in puddles, people with umbrellas crossing. Slow crane down. Rain and traffic.
Wind moves across a lavender field at sunset, bees drifting between flowers. Slow dolly forward. Wind and humming bees.
Hundreds of paper lanterns rise into a night sky over a river, reflections shimmering. Slow tilt up. Soft crowd murmur and water.
Iced tea pours from the jug in image 1 into the glass in image 2, ice cubes clinking and settling. Macro, backlit. Pouring and clinks.
The woman from image 1 turns her head quickly and her hair swings and settles. Slow motion, soft light. Quiet whoosh.
The man from image 1 swings the bag from image 2 over his shoulder and walks off down the street. Medium shot. Footsteps and traffic.
The curtains in the room from image 1 billow as the window opens and light floods in. Camera still. Wind and birds.
A gust scatters the papers on the desk from image 1 into the air; they flutter down slowly. Camera still. Rustling paper.
Upload them in order and refer to each by number in the prompt, for example “the woman from image 1 wears the jacket from image 2”.
Up to nine reference images. In practice three to five clean references give the most reliable result.
Yes. Text-to-video needs only a prompt, and image-to-video needs one photo.
The single-image and text prompts work across AI Video Pro. Prompts with several numbered references need an engine that accepts references.
Yes. GoCrazyAI is for adults (18+) only. Prompts that break the community guidelines are blocked automatically, and uploads are checked before generation.
HappyHorse 1.1 opens preselected in AI Video Pro. The credit cost shows before you generate.
Last updated: