Skip to main content

MiniMax’s open-weights H3-Image generates a still from a prompt and applies up to three LoRA files, each with its own 0–4 strength, across five size tiers from 1K to 4K and 15 aspect ratios.

From $0.042/image

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • vhs-motel-red-dressOutput
    vhs-motel-red-dress

    At 1k, 16:9 and seed 11, the scale-1 VHS LoRA produced a woman dancing in a red slip dress in a motel room. The frame has the soft 1990s camcorder treatment associated with vh5tape.

    • 11
    • 1k
    • 16:9
  • vhs-diner-danceOutput
    vhs-diner-dance

    At scale 1, seed 21 and 1.5k, the diner dance had a grainy tape treatment plus vh5tape lettering in the lower-left corner.

    • 21
    • 1.5k
    • 16:9
  • vhs-mall-arcadeOutput
    vhs-mall-arcade

    The scale-1 VHS request used seed 11 at 1.5k, showing two players at a racing cabinet with soft recording blur.

    • 11
    • 1.5k
    • 16:9

This example starts at $0.042 per image. The Playground updates the estimate when you change the settings.