# MiniMax H3 Image (https://docs.fuser.studio/docs/nodes/image/minimax-h3-image)

_Provided by [Fal](https://fal.ai) — [Learn More](https://fal.ai/models/minimax/h3-image/text-to-image)._

Model page: https://fuser.studio/models/minimax-h3-image

## Inputs [#inputs]

- **Prompt** (`textarea`) — Describe the image to generate, or the edit to make. Refer to reference images as "Image 1", "Image 2" and so on, in the order they are connected.

- **Images** (`image`) _(accepts multiple)_ — Up to 16 reference images to edit or combine. Leave empty to generate from text.

   Optional: `true`

- **Model** (`dropdown`) — Highspeed renders faster at about twice the price.

   Optional: `true` • Default: `h3-image` • Accepts: `H3 Image`, `H3 Image Highspeed`

- **Resolution** (`dropdown`) — Output resolution. 4K costs about four times as much as 2K.

   Optional: `true` • Default: `2k` • Accepts: `2K`, `4K`

- **Aspect Ratio** (`dropdown`) — Shape of the generated image. "Auto" is square from text, and keeps the first reference image's shape at 2K when editing.

   Optional: `true` • Default: `auto` • Accepts: `Auto`, `3:1`, `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`, `9:21`, `1:3`

- **Expand Prompt** (`toggle`) — Rewrite a text prompt into a detailed description before generating. Edits always expand.

   Optional: `true` • Default: `true`

- **Output Format** (`dropdown`) — The file format for the output image.

   Optional: `true` • Default: `png` • Accepts: `PNG`, `JPEG`, `WebP`

## Outputs [#outputs]

- **Generated Image** (`image`) — The generated image from the model.