---
title: "A picture from a sentence"
description: "Make an image from a prompt."
sidebar:
  label: generate
---

{/* Generated by scripts/generate-commands.ts. Do not edit. */}

## Synopsis

```sh
motif [prompt] [options]
```

## Example

Two bottles and a dish, made from the sentence.

```sh
motif "amber bottles and a brass dish on a walnut shelf"
```

<div class="docs-pictures docs-pictures-1">
  <figure>
    <img src="/docs/images/commands/hero.jpg" alt="Two amber glass bottles, one holding dried flowers, and a small brass dish on a walnut shelf, with low sun across a green wall" loading="lazy" />
    <figcaption>Result</figcaption>
  </figure>
</div>

## Options

| Flag | What it does |
| --- | --- |
| `--dry-run` | Validate inputs without making API calls. |
| `--ephemeral` | Save output locally, then delete fal request IO payloads when possible. |
| `--tier <tier>` | Trade cost against quality: fast, balanced, quality. |
| `-e, --edit <file>` | Reference image for editing; repeat for more (-e a.png -e b.png). |
| `-a, --aspect <ratio>` | Aspect ratio (auto, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 4:5, 5:4, 21:9, 4:1, 1:4, 8:1, 1:8). |
| `-r, --resolution <res>` | Resolution (0.5K, 1K, 2K, 4K). |
| `-n, --num <count>` | Number of images 1-4. |
| `--cover` | Kindle/eBook cover: 2:3, 2K (1600×2400). |
| `--square` | Square: 1:1. |
| `--landscape` | Landscape: 16:9. |
| `--portrait` | Portrait: 2:3. |
| `--story` | Instagram/TikTok Story: 9:16 (1080×1920). |
| `--reel` | Instagram Reel: 9:16 (1080×1920). |
| `--feed` | Instagram Feed portrait: 4:5 (1080×1350). |
| `--og` | Open Graph / social share: 16:9 (1200×630). |
| `--wallpaper` | iPhone wallpaper: 9:16. |
| `--wide` | Cinematic wide: 21:9. |
| `--ultra` | Ultra-wide banner: 21:9, 2K. |
| `--transparent` | Transparent background PNG. |
| `--mask <path>` | Mask image for an edit with -e. |
| `--markup <path>` | Markup for an edit with -e: a transparent PNG of arrows, circles and notes. |
| `--negative <text>` | Negative prompt: what not to include. |
| `--output-format <format>` | Output format: jpeg, png, webp, gif, svg. |
| `--look <id>` | House look id, e.g. editorial. |
| `--mood <id>` | Light mood id, e.g. overcast. |
| `--no-mood` | Drop any mood, including one from stdin JSON. |

It also takes the [common options](/docs/commands#common-options).

## Models and price

Motif picks the Model for the Tier. Prices are per image where a Model has one; any other shows how it is billed. A rate that depends on the size of the file or the length of the clip is a rate, not a total, so check it with a dry run.

| Model | Chosen at | Price |
| --- | --- | ---: |
| Nano Banana 2.1 | Balanced | Billed by use |
| Grok Imagine Image 2.0 | Balanced | $0.060 |
| Meta Muse Image | Balanced | $0.010 |
| Nano Banana 2 | Balanced | $0.080 |
| Qwen Image 3 | Balanced | $0.040 |
| MAI Image 2.5 | Balanced | Billed by use |
| Nano Banana Pro | Balanced | $0.150 |
| Ideogram V4 | Balanced | $0.030 |
| FLUX.2 Flex | Balanced | $0.050 |
| Recraft V4.1 | Balanced | $0.035 |
| FLUX.2 Pro | Balanced | $0.030 |
| Krea 3 | Balanced | $0.025 |
| Grok Imagine Image Quality | Balanced | $0.050 |
| Ideogram V3 Transparent | Balanced, for transparent output | $0.060 |
| Nano Banana 2 Lite | Fast | Billed by use |
| Grok Imagine Image | Fast | $0.020 |
| Seedream 5.0 Lite | Fast | $0.035 |
| FLUX.2 Turbo | Fast | $0.008 |
| GPT Image 2.6 Sunburst | Quality | Billed by use |
| GPT Image 2.6 Flare | Quality | Billed by use |
| Seedream 5.0 Pro | Quality | $0.068 |
| GPT Image 1.5 | Quality | $0.133 |
| MAI Image 2.5 Pro | Quality | $0.170 |

## Dry run

Check the cost before you spend. The output path is where the file would go.

```sh
motif "amber bottles and a brass dish on a walnut shelf" --dry-run --fields cost,costBasis,output
```

```json
{
  "cost": null,
  "costBasis": "unknown",
  "output": "motif-20261109104301.png"
}
```