Skip to main content

Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.Browse every model at this filtering level
minimax/h3-image-lora/edit

MiniMax H3 Image LoRA image editing takes one to nine reference images, a description of the change and up to three of your own LoRAs. Identity carries over into a new scene, outfit, pose or style at about 1 or 4 megapixels.

From $0.054/image
Run model

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.

  • same-woman-named-refsOutput
    same-woman-named-refs

    One portrait as <Picture 1> and a new setting in words. Face and hairstyle come from the reference; clothes, light and place are new.

    • 42
    • 1k
    • 3:4
  • same-woman-new-sceneOutput
    same-woman-new-scene

    One portrait as Picture 1 and a new setting in words. Face and hairstyle come from the reference; clothes, light and place are new.

    • 42
    • 1k
    • 3:4
  • singer-as-1939-cartoonOutput
    singer-as-1939-cartoon

    A cartoon style LoRA with its trigger word. The pose, the dress and the microphone survive the change of medium.

    • 42
    • 1k

This example starts at $0.054 per image. The Playground updates the estimate when you change the settings.