Skip to content

MiniMax H3 / Text to video

MiniMax H3 product reveal video: a controlled studio workflow

Create a short product reveal by keeping the product still and giving the camera one simple movement. This separates the visual idea from the harder problem of making an object rotate convincingly. It is a useful starting point for concept advertising, especially before you have a final product photograph.

By JollyAIReviewed 2 min read

Plan a reveal that fits one shot

A pedestal, one subject and a single lighting change give the viewer a clear focal point. Decide what the reveal should communicate: the outline of a shoe, the texture of fabric or the shape of a bottle. Do not ask the same short clip to introduce a product, demonstrate it, change locations and display a sales message.

For an exact item from your catalogue, use image-to-video with an approved photograph instead. Text-to-video invents a product; it cannot establish that an invented shape, material or feature matches something you sell.

Build the shot in JollyAI

  1. Select MiniMax H3 Text to Video and choose a landscape or portrait composition before writing the prompt.
  2. Name the product, support surface and background. Keep these descriptions short enough that the movement remains prominent.
  3. Add one camera instruction, such as a slow lateral slide, and one secondary effect, such as drifting mist.
  4. Generate a draft and inspect the silhouette at the beginning, middle and end. Reject clips in which the sole, cap or handle changes shape.

A prompt to adapt

PROMPT RECIPE / ADAPT TO YOUR SOURCE

An unbranded acid-green sports shoe rests on a charcoal pedestal against a black studio background. The camera slides slowly from left to right through a modest angle. A narrow white light reveals the mesh texture once. The shoe stays stationary. Soft mist behind the pedestal. One continuous product shot. Sound: a quiet airy whoosh.

Finish the advertisement

Place price, logo and call to action in your editor after choosing the shot. This lets you correct copy without regenerating the footage. Leave a short still hold at the end if the viewer needs time to read an offer. The demonstration on this page is a generated concept product, not a photographed commercial item.

REVIEWED JOLLYAI IMPLEMENTATION

The workflow behind the guide

Written scene → text conditioning → turbo audio/video sampling → separate video and audio decoding → combined video file.

Inputs, presets & access
Limited free access; four-second free preset, with six/eight/ten-second PRO options. Current ordinary pixel budget: 0.4 MP. Use the account controls for current availability.
Implementation note
Local H3 turbo workflow. Six sampling steps; simple scheduler; turbo adapter; video/audio shifts 12/3. Current environment: pruned W4A8 FL2VA weights with a 4B encoder and matching projection. R2V uses a separate reference checkpoint. These settings describe the reviewed JollyAI deployment, not every H3 implementation.

Configuration reviewed September 20, 2026. Your current playground controls and plans page determine availability. Prompt recipes above are suggestions, not guarantees or claimed test results.

Open Text to video ↗

ORIGINAL JOLLYAI GENERATION

A five-second request, inspected as a real file

A fictional green sports shoe on a dark pedestal; the viewpoint shifts as light and mist move. Generated ambience, no dialogue. Selected concept-product example. The shoe remains recognizable, but the viewpoint changes more than a strict lateral slide and some fine details vary. Inspect the full clip; this is not a fidelity guarantee or a matched benchmark.
Request
5 seconds / 0.4 MP
Delivered file
864 × 480 / 24 fps / 5.167 s
Audio
Generated audio stream
Queue wait
22 seconds
Processing interval
115 seconds
End to end
137 seconds

One owner-account observation, September 20, 2026. Processing is the recorded job interval, including pipeline overhead, not isolated sampling time. Other requests and settings can differ. Five seconds was an administrator request; public H3 presets currently use 4/6/8/10 seconds.

Exact demonstration prompt

One continuous studio product film of a fictional unbranded acid-green sports shoe resting on a matte charcoal pedestal. The camera slowly slides from left to right through a modest angle while the shoe remains stationary. A thin veil of pale mist drifts behind the pedestal. A narrow white light sweeps across the fabric texture once, revealing the mesh and sole. Clean black background, sharp silhouette, believable proportions, premium commercial photography, no writing or logos. Sound: a soft airy whoosh and quiet studio ambience. Landscape 16:9.

Sources and useful next steps

The implementation notes describe JollyAI's reviewed local integration. Upstream capabilities and licences may differ from the settings available here.

Found an outdated setting or a reproducible problem? Contact JollyAI with the workflow and job reference. Keep account tokens and private input files out of public reports.

KEEP BUILDING

Continue the workflow.