[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [HiDream O1 Image Dev](https://spiral.ai/integrations/chatgpt/hidream-o1-image-dev)

# How to Use HiDream O1 Image Dev in ChatGPT

HiDream O1 Image Dev creates images from written briefs and can use references for edits or subject consistency. Unlike HiDream O1 Image Dev Edit, it can start without a reference image.

|  |  |
| --- | --- |
| Model | HiDream O1 Image Dev |
| Available through | fal |
| Category | Image |
| Price | $0.0065 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 O1 Image Dev in ChatGPT

- Use HiDream O1 Image Dev to make a square poster showing a red canoe on a quiet lake. Put "Paddle day" at the top in large white lettering and "Saturday at noon" along the bottom.
- Use HiDream O1 Image Dev with these character references to show the character reading in a library. Place the character in the foreground on the right and bookshelves in the background.
- Use HiDream O1 Image Dev to create a 2048 × 2048 storyboard with four panels: a gardener planting a seed, watering it, seeing a sprout, and picking a tomato. Use clear panel boundaries and no captions.
- Generate a product photo with HiDream O1 Image Dev: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first.
- Make four logo concepts for a coffee brand called "Northline" with HiDream O1 Image Dev.

## How to set up HiDream O1 Image Dev in ChatGPT

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

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT 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 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 O1 Image Dev**: 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-o1-image/dev",
    "input": {
      "prompt": "A cinematic product photo of a ceramic mug on a marble counter, soft window light, shallow depth of field."
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds HiDream O1 Image Dev on Spiral, shows the price and runs it.

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

## HiDream O1 Image Dev tools and prices

- [Hidream O1 Image](https://spiral.ai/tools/fal/fal-ai/hidream-o1-image/dev) (fal): $0.0065 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 |
| --- | --- | --- | --- |
| reference_image_urls |  | [] | Optional reference images. Use none for text-to-image, one for image editing, or multiple for subject-driven personalization. |
| image_size |  | {"width":1024,"height":1024} | Requested output image size. Dimensions are rounded down to a multiple of 32, up to about 2048x2048 pixels. |
| num_inference_steps | 1 to 28 | 28 | Number of denoising steps. The dev model is distilled for 28 steps. |
| guidance_scale | 0 to 20 | 0 | Classifier-free guidance scale. The dev model uses 0.0 by default. |
| seed |  | — | Random seed for reproducible generation. |
| num_images | 1 to 4 | 1 | Number of images to generate. |

## What can you do with HiDream O1 Image Dev in ChatGPT?

Turn a visual brief into artwork or revise an image through a conversation. A chat app can help specify composition, exact wording, and the details to preserve before generation.

### Product scene concepts

Place a referenced product in a new setting, such as a ceramic mug on a breakfast table. Specify the product's position and which visible details to preserve.

### Character scene illustrations

Use character references to illustrate a new scene. Describe the character's appearance, action, and position explicitly, then review identity consistency.

### Poster revisions

Revise existing poster artwork with supplied headlines and a planned reading order. Identify the exact text and its intended location.

### Storyboard sheets

Turn a referenced subject and scene brief into a storyboard image containing multiple panels. Describe each panel's action and composition separately.

### Object replacements

Replace an object in an existing image through a written instruction. State the replacement clearly and identify the surrounding details to preserve.

### Campaign scene exploration

Reuse referenced subjects across proposed campaign scenes. Compare backgrounds and compositions while keeping the subject description consistent.

## Overview

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

## HiDream O1 Image Dev in other agents

- [Amp](https://spiral.ai/integrations/amp/hidream-o1-image-dev)
- [Claude](https://spiral.ai/integrations/claude-desktop/hidream-o1-image-dev)
- [Claude Code](https://spiral.ai/integrations/claude-code/hidream-o1-image-dev)
- [Cline](https://spiral.ai/integrations/cline/hidream-o1-image-dev)
- [Codex](https://spiral.ai/integrations/codex/hidream-o1-image-dev)
- [Cursor](https://spiral.ai/integrations/cursor/hidream-o1-image-dev)
- [Devin](https://spiral.ai/integrations/devin/hidream-o1-image-dev)
- [dots](https://spiral.ai/integrations/dots/hidream-o1-image-dev)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/hidream-o1-image-dev)
- [Gemini](https://spiral.ai/integrations/gemini/hidream-o1-image-dev)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/hidream-o1-image-dev)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/hidream-o1-image-dev)
- [goose](https://spiral.ai/integrations/goose/hidream-o1-image-dev)
- [Grok](https://spiral.ai/integrations/grok/hidream-o1-image-dev)
- [Grok Build](https://spiral.ai/integrations/grok-build/hidream-o1-image-dev)
- [Hermes](https://spiral.ai/integrations/hermes/hidream-o1-image-dev)
- [Instinct](https://spiral.ai/integrations/instinct/hidream-o1-image-dev)
- [Manus](https://spiral.ai/integrations/manus/hidream-o1-image-dev)
- [Muse](https://spiral.ai/integrations/muse/hidream-o1-image-dev)
- [Muse Code](https://spiral.ai/integrations/muse-code/hidream-o1-image-dev)
- [n8n](https://spiral.ai/integrations/n8n/hidream-o1-image-dev)
- [Notion](https://spiral.ai/integrations/notion/hidream-o1-image-dev)
- [OpenClaw](https://spiral.ai/integrations/openclaw/hidream-o1-image-dev)
- [opencode](https://spiral.ai/integrations/opencode/hidream-o1-image-dev)
- [Perplexity](https://spiral.ai/integrations/perplexity/hidream-o1-image-dev)
- [Raycast](https://spiral.ai/integrations/raycast/hidream-o1-image-dev)
- [VS Code](https://spiral.ai/integrations/vscode/hidream-o1-image-dev)
- [Windsurf](https://spiral.ai/integrations/windsurf/hidream-o1-image-dev)
- [Zapier](https://spiral.ai/integrations/zapier/hidream-o1-image-dev)

## More ChatGPT guides

- [HiDream O1 Image](https://spiral.ai/integrations/chatgpt/hidream-o1-image)
- [HiDream O1 Image Dev Edit](https://spiral.ai/integrations/chatgpt/hidream-o1-image-dev-edit)
- [HiDream I1 Full](https://spiral.ai/integrations/chatgpt/hidream-i1-full)
- [HiDream O1 Image Edit](https://spiral.ai/integrations/chatgpt/hidream-o1-image-edit)
- [HiDream I1 Fast](https://spiral.ai/integrations/chatgpt/hidream-i1-fast)
- [HunyuanImage 2.1](https://spiral.ai/integrations/chatgpt/hunyuanimage-2-1)

## Questions about HiDream O1 Image Dev in ChatGPT

**Can ChatGPT use HiDream O1 Image Dev?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run HiDream O1 Image Dev like any built-in tool.

**How much does HiDream O1 Image Dev cost in ChatGPT?**

$0.0065 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 ChatGPT plan is separate.

**Do I need a fal account to use HiDream O1 Image Dev in ChatGPT?**

No. Spiral runs HiDream O1 Image Dev 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 O1 Image Dev in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while HiDream O1 Image Dev runs?**

HiDream O1 Image Dev runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.

**What is HiDream O1 Image Dev useful for?**

Use it for images with planned text placement, changes to existing artwork, and new scenes featuring referenced subjects. Storyboard sheets are another documented use.

**How large can HiDream O1 Image Dev images be?**

Plan for output up to approximately 2048 × 2048 pixels. Reference-based results use the nearest supported resolution, so check the returned dimensions before placing an image in a fixed layout.

**Can HiDream O1 Image Dev put text in images?**

HiDream documents multilingual text rendering and placement across multiple regions. Include the exact wording, reading order, and intended location, then proofread the result before using it.

**How should I describe a composition?**

Specify where each important element belongs: foreground, background, top left, or bottom edge. For text, provide the complete copy and reading order instead of asking the model to invent them.

**Which generation settings should I start with?**

Start with 28 steps and guidance at zero, matching the maker's Dev inference recipe. Treat that as your baseline when comparing prompt revisions.

