See it made
Run it in Scenario
About this use case
9:16 ads in three parts (a generated hook, a gameplay body, an end card), so you can test a new hook and keep the rest: user acquisition ads live or die in the first two seconds. The game is Pipsqueen by Brightkeep Games, a cozy kingdom builder. The models and settings in this use case are as of October 2026.
See moreSee less
- Two vertical game ads that share one gameplay body and end card and differ only in their generated hook.
- Generate only the hook from an approved still; build the body and end card from real game assets in code.
- Each new hook is one short video generation; the body, captions and end card are reused at no cost.
Step by step with an agent, through the Scenario MCP (6 steps)Hide the steps
Connect the Scenario MCP
Connect your agent and sign in once at mcp.scenario.com. Then tell it which Scenario team and project to use, so every file lands there.
Give the agent the files
Queen Pip's approved character image first, then the key art for the world and the style; for hook B, the game's gold coin and the town hall. Add the real game assets for the body and the end card (the stable at levels 1 and 2, the coins, the progress bar, the three-slice button), the music loop and the sound effects. A local agent reads them from a folder and uploads the images with upload_asset.
Brief the agent: the first frames
Each hook starts as a still with the safe zones written into the prompt: the platform puts its buttons at the top and bottom, and the caption goes there too.
PromptMake the first frame of hook A with GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst). Pass referenceImages as an array: Queen Pip first, the key art second. Size 1152 x 2048 (9:16). Quote the cost with a dry run first and wait for my go. Prompt, word for word: Reference 1 is Queen Pip: copy her face, brown hair bun, oversized tilted gold crown, ermine cloak, blue and gold dress and toy-mace scepter exactly. Reference 2 is the world and the art style. Vertical mobile ad frame: Queen Pip rides her shaggy white battle goat with curled horns straight toward the camera across a green meadow, scepter raised high, cloak flying, mouth open in a fierce battle cry; a line of stubby knights with round blue shields charges behind her and a wooden goblin fort stands far behind. Low camera, dynamic, bright sunny sky. The queen and the goat sit in the middle third of the frame; keep the top 15 percent as open sky and the bottom 20 percent as plain grass with no important detail. No text, no letters, no logo, no UI. Then make hook B's first frame the same way, with the gold coin and the town hall as references: a wooden treasure chest bound in blue-painted iron bursting open in the cobbled square in front of the round stone keep, gold crown coins spraying toward the camera, and the same last two sentences about the safe zones and no text. Show me both stills before you animate anything.Animate each hook
In the first take the scepter swung across her face and turned into a smear, so the prompt says where it stays.
PromptAnimate both approved stills with MiniMax H3 (model_minimax-h3): firstFrameImage set to the still, duration 5, resolution "768P". Start both with wait: false and collect them with one jobs_wait. Quote the cost first and wait for my go. Hook A prompt, word for word: Vertical mobile game ad, the first second must grab attention. The little queen rides her shaggy battle goat straight toward the camera at full gallop, shouting a battle cry, cloak streaming behind her; the knights charge behind her. The camera pulls back fast and low ahead of the goat. She holds her scepter raised high above her crown the whole time and shakes it there; the scepter never passes in front of her face, and her face stays sharp and fully visible. Keep her face, crown, ermine cloak, blue dress and scepter, and the goat's curled horns and harness, exactly as in the first frame. Chunky stylized 3D game art, bright sunny light. No text. Hook B prompt, word for word: The treasure chest bursts open wider and a fountain of gold crown coins sprays straight toward the camera, coins spinning and tumbling past the lens, sparkles in the air, more coins landing and bouncing on the cobblestones. The camera is locked. Keep the chest, the gold coin design with the embossed crown and the stone keep behind exactly as in the first frame.Check the hooks, then build the ad in code
Accept when motion starts in the first frame, the queen, goat or chest keeps its design, hands and faces are intact in every frame, and nothing smears across a face. Reject a morph, a smear or motion that runs backward, and rerun only that hook. The body and the end card are not generated: they show the real game.
PromptCheck each hook frame by frame and tell me if the character or the chest changes design, if anything passes in front of her face, or if the motion runs backward. Then, in code: build a 4.5 second body from the real assets (a tap on the level 1 stable, six coins flying from the counter from 1,500 down to 900, the progress bar filling, a flash, the level 2 stable with a bounce, the level ring with a 2, the knight hopping in, caption "Upgrade your village"), and an end card with the PIPSQUEEN title, "Build your kingdom", a "Pre-register" button from the three-slice button and one availability line. Conform everything to 1080 x 1920 at 30 fps, trim each hook to its first 3.8 seconds, add its caption ("Charge into battle!" or "Open the royal treasury"), join hook, body and end card, replace the hook audio with the music loop and the sound effects, and export H.264 with AAC.Review with the sound off and report
The story must read from images and captions alone, on a phone-sized preview. MiniMax H3 adds its own sound, so check that none of it is left in the mix. The call to action must match what the store offers right now.
PromptRun speech-to-text on each hook alone and confirm none of its audio is in the final mix. Check that no caption covers a face or sits in the top 15 percent or bottom 20 percent of the frame. Create a collection for this campaign with the two stills and the two hooks, and report the models, every asset ID, the paths of the two exported ads and the total cost spent.
Step by step in the web app (7 steps)Hide the steps
A vertical first frame
Each hook starts as a still. Create › Images › GPT Image 2.5 Sunburst, Reference Images › Select from Library › Queen Pip, Dimensions 9:16.
Write the safe zones into the prompt
She charges straight at the camera, and the prompt keeps the top and bottom of the frame empty, because that's where the platform puts its buttons and where the caption will go.
PromptReference 1 is Queen Pip: copy her face, brown hair bun, oversized tilted gold crown, ermine cloak, blue and gold dress and toy-mace scepter exactly. Reference 2 is the world and the art style. Vertical mobile ad frame: Queen Pip rides her shaggy white battle goat with curled horns straight toward the camera across a green meadow, scepter raised high, cloak flying, mouth open in a fierce battle cry; a line of stubby knights with round blue shields charges behind her and a wooden goblin fort stands far behind. Low camera, dynamic, bright sunny sky. The queen and the goat sit in the middle third of the frame; keep the top 15 percent as open sky and the bottom 20 percent as plain grass with no important detail. No text, no letters, no logo, no UI.One still per hook
Hook A is the queen, hook B a treasure chest bursting with coins, with the same safe zones. Only the hook changes; both ads share the same body and end card.
Animate from the first frame
Create › Videos › Minimax H3, hook A's still in First Frame, Duration 5 s, Resolution 768P. The prompt says the first second must grab attention and where the scepter stays: in the first take it swung across her face and turned into a smear.
PromptVertical mobile game ad, the first second must grab attention. The little queen rides her shaggy battle goat straight toward the camera at full gallop, shouting a battle cry, cloak streaming behind her; the knights charge behind her. The camera pulls back fast and low ahead of the goat. She holds her scepter raised high above her crown the whole time and shakes it there; the scepter never passes in front of her face, and her face stays sharp and fully visible. Keep her face, crown, ermine cloak, blue dress and scepter, and the goat's curled horns and harness, exactly as in the first frame. Chunky stylized 3D game art, bright sunny light. No text.Real game assets, animated in code
The body isn't generated: it shows the real game (the stable, the coins, the progress bar) animated frame by frame in code, so the numbers are exact and the caption is easy to translate.
An end card that matches the store
The end card is code too: the title, a button and one availability line. The call to action must match what the game offers right now.
Join, caption, mix
A script joins the three parts, adds each hook's caption, and mixes the music and sound effects at fixed points. A new variant is one line: a new hook file and its caption.



