MiniMax | H3 | Max | Turbo | Text to Video

curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "minimax-h3-max-turbo-text-to-video",
    "version": "0.0.1",
    "input": {
        "prompt": "A 10 second scene in a rustic Swedish farmhouse kitchen before sunrise. One woman, one kitchen, same lighting throughout. Only one cut in the entire video.\n\nThe woman is in her mid twenties, Scandinavian, fair skin with light freckles, pale grey blue eyes, dark blonde hair loosely tied back with a few strands falling across her face. Bare face, no makeup. Thick oatmeal wool cardigan with sleeves pushed to her elbows, heavy linen apron dusted with flour. Calm and focused, slightly sleepy.\n\nWorn wooden table, a stone oven with its mouth open and glowing, a small frosted window on the left. Cold blue dawn light from the window, warm orange firelight from the oven. Flour dust hanging in the air. Photoreal, 50mm lens, shallow depth of field.\n\n0 to 5s: Medium close up from the side. She kneads dough on the floured table with slow, deliberate movements. Press forward, fold, quarter turn. Flour puffs up on each push. A loose strand of hair falls across her face and she blows it away without stopping. Her hands stay in frame and in focus the whole time.\n\n5 to 10s: One cut to a wider shot as she slides the shaped loaf into the glowing oven with a wooden peel, then straightens up and looks at the fire. The camera holds still.\n\nRealistic human hands with five fingers, correct anatomy, natural grip on the dough and the peel. Consistent face and clothing before and after the cut. Real time speed, no slow motion, no speed ramping. Natural handheld feel with subtle movement. Sounds of dough on wood and crackling fire. No music, no dialogue.",
        "duration": 10,
        "resolution": "768P",
        "aspect_ratio": "16:9",
        "enable_safety_checker": true,
        "prompt_expansion_mode": "quality"
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/