[Integrations](https://spiral.ai/integrations) › [OpenClaw](https://spiral.ai/integrations/openclaw) › [HiDream I1 Full](https://spiral.ai/integrations/openclaw/hidream-i1-full)

# How to Use HiDream I1 Full in OpenClaw

HiDream I1 Full creates photos, cartoons, and illustrations from detailed scene descriptions. It prioritizes image quality over the shorter generation schedules used by HiDream I1 Dev and HiDream I1 Fast.

|  |  |
| --- | --- |
| Model | HiDream I1 Full |
| Available through | fal |
| Category | Image |
| Price | $0.065 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with HiDream I1 Full in OpenClaw

- Every Monday, use HiDream I1 Full to create a 1024 × 1024 watercolor illustration for an indoor gardening tip. Choose one herb and one gardening tool, use muted greens and terracotta, and include the scene description with the result.
- Each Friday, use HiDream I1 Full to generate a 1360 × 768 painted landscape for a weekend reading post. Rotate between a lakeside cabin, a city park, and a coastal path; leave open space on the left for text added later.
- On the first day of each month, use HiDream I1 Full to create a 768 × 1360 seasonal illustration for a bookstore: one reader, one book, and a setting suited to the month. Use a painted style and send the result for review.
- Every Wednesday, use HiDream I1 Full to make a 1024 × 1024 cartoon for a cycling newsletter: one cyclist in a red jacket beside a blue bicycle. Change the setting each week and flag any incorrect color assignments.
- Each morning, use HiDream I1 Full to create a 1360 × 768 photorealistic still life for a cafe's draft social post: one cup and one pastry beside a window. Use 50 generation steps and prompt guidance of 5, then return it for review.

## How to set up HiDream I1 Full in OpenClaw

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send OpenClaw this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use Spiral's MCP server

1. **Add the server**: On the machine that runs OpenClaw's Gateway:

```bash
openclaw mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --transport streamable-http \
  --auth oauth
```

2. **Sign in**: In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

```bash
openclaw mcp login spiral
```

3. **Reload and check**: A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

```bash
openclaw mcp reload
openclaw mcp doctor spiral --probe
```

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run HiDream I1 Full**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/hidream-i1-full",
    "input": {
      "prompt": "a cat holding a skateboard which has '\''fal'\'' written on it in red spray paint"
    }
  }'
```

Then paste one of the prompts above: OpenClaw finds HiDream I1 Full on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/openclaw

## HiDream I1 Full tools and prices

- [Hidream I1 Full · Text to Image](https://spiral.ai/tools/fal/fal-ai/hidream-i1-full) (fal): $0.065 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| negative_prompt |  |  | The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). |
| image_size |  | {"width":1024,"height":1024} | The size of the generated image. |
| num_inference_steps | 1 to 50 | 50 | The number of inference steps to perform. |
| seed |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| guidance_scale | 0 to 20 | 5 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| num_images | 1 to 4 | 1 | The number of images to generate. |

## What can you do with HiDream I1 Full in OpenClaw?

Produce recurring artwork from a standing creative brief. A scheduled agent can prepare images for review while checking the requested subjects, colors, and composition.

### Article illustrations

Create an illustration for an article about urban gardening, such as a gardener tending tomatoes on an apartment balcony. Specify the medium, palette, and main action.

### Website hero artwork

Generate a landscape scene with the subject on one side and open space for a headline. Check the placement before adding the text in your page layout.

### Product scene concepts

Explore lighting and settings for an imagined product, such as a plain ceramic mug on a breakfast table. Use the results to plan a shoot or discuss an art direction.

### Character concept art

Describe a character's clothing, pose, surroundings, and illustration style to develop an initial visual direction for a game or story.

### Social post artwork

Create square illustrations for a series of gardening tips or seasonal announcements. Repeat the palette and medium in each brief, then review the images together.

### Story scene planning

Turn a written scene into an image for discussing framing, setting, and mood. Keep the main action clear and check object relationships against the brief.

### Composition studies

Compare simple arrangements of two colored objects before committing to an illustration. Inspect positions and color assignments rather than assuming every instruction was followed.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All OpenClaw guides](https://spiral.ai/integrations/openclaw)

## HiDream I1 Full in other agents

- [Amp](https://spiral.ai/integrations/amp/hidream-i1-full)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/hidream-i1-full)
- [Claude](https://spiral.ai/integrations/claude-desktop/hidream-i1-full)
- [Claude Code](https://spiral.ai/integrations/claude-code/hidream-i1-full)
- [Cline](https://spiral.ai/integrations/cline/hidream-i1-full)
- [Codex](https://spiral.ai/integrations/codex/hidream-i1-full)
- [Cursor](https://spiral.ai/integrations/cursor/hidream-i1-full)
- [Devin](https://spiral.ai/integrations/devin/hidream-i1-full)
- [dots](https://spiral.ai/integrations/dots/hidream-i1-full)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/hidream-i1-full)
- [Gemini](https://spiral.ai/integrations/gemini/hidream-i1-full)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/hidream-i1-full)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/hidream-i1-full)
- [goose](https://spiral.ai/integrations/goose/hidream-i1-full)
- [Grok](https://spiral.ai/integrations/grok/hidream-i1-full)
- [Grok Build](https://spiral.ai/integrations/grok-build/hidream-i1-full)
- [Hermes](https://spiral.ai/integrations/hermes/hidream-i1-full)
- [Instinct](https://spiral.ai/integrations/instinct/hidream-i1-full)
- [Manus](https://spiral.ai/integrations/manus/hidream-i1-full)
- [Muse](https://spiral.ai/integrations/muse/hidream-i1-full)
- [Muse Code](https://spiral.ai/integrations/muse-code/hidream-i1-full)
- [n8n](https://spiral.ai/integrations/n8n/hidream-i1-full)
- [Notion](https://spiral.ai/integrations/notion/hidream-i1-full)
- [opencode](https://spiral.ai/integrations/opencode/hidream-i1-full)
- [Perplexity](https://spiral.ai/integrations/perplexity/hidream-i1-full)
- [Raycast](https://spiral.ai/integrations/raycast/hidream-i1-full)
- [VS Code](https://spiral.ai/integrations/vscode/hidream-i1-full)
- [Windsurf](https://spiral.ai/integrations/windsurf/hidream-i1-full)
- [Zapier](https://spiral.ai/integrations/zapier/hidream-i1-full)

## More OpenClaw guides

- [HiDream I1 Fast](https://spiral.ai/integrations/openclaw/hidream-i1-fast)
- [HiDream O1 Image](https://spiral.ai/integrations/openclaw/hidream-o1-image)
- [Hi3D Image to Relief](https://spiral.ai/integrations/openclaw/hi3d-image-to-relief)
- [HiDream O1 Image Dev](https://spiral.ai/integrations/openclaw/hidream-o1-image-dev)
- [Headshot Generator](https://spiral.ai/integrations/openclaw/headshot-generator)
- [HiDream O1 Image Dev Edit](https://spiral.ai/integrations/openclaw/hidream-o1-image-dev-edit)

## Questions about HiDream I1 Full in OpenClaw

**Can OpenClaw use HiDream I1 Full?**

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run HiDream I1 Full like any built-in tool.

**How much does HiDream I1 Full cost in OpenClaw?**

$0.065 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

**Do I need a fal account to use HiDream I1 Full in OpenClaw?**

No. Spiral runs HiDream I1 Full on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up HiDream I1 Full in OpenClaw?**

About two minutes: add the server, then sign in, then reload and check.

**Does OpenClaw wait while HiDream I1 Full runs?**

HiDream I1 Full runs in the background. OpenClaw starts the run, checks on it and gives you the image when it's ready.

**What is HiDream I1 good at?**

HiDream I1 creates photorealistic scenes, cartoons, and artistic illustrations. Use it for visual briefs that specify the subject, colors, and relationships between a few objects.

**How does HiDream I1 Full differ from Dev and Fast?**

HiDream I1 Full prioritizes image quality. HiDream I1 Dev uses guidance distillation, while HiDream I1 Fast uses a shorter generation schedule.

**What image sizes should I start with?**

The maker demonstrates 1024 × 1024 for square images, 768 × 1360 for portraits, and 1360 × 768 for landscapes. Choose the shape that fits the intended placement before refining the composition.

**Can I trust exact object counts and positions?**

Review both before using the image. The maker's GenEval results show stronger performance on two-object scenes and colors than on exact positioning, so treat spatial instructions as requests that need checking.

**Which settings are worth adjusting?**

For HiDream I1 Full, start with the maker's 50 steps and guidance of 5. If the result misses your description, test a small guidance increase and compare the result for visual quality.

