Weekly

Generate weekly social images with OpenAI

Each week a set of images for your planned topics, made in your style, arrives in your inbox as links.

Runs: Weekly
Apps: OpenAI
AI: Not needed
Access: API key (All, or Restricted with image access)

Send this to your assistant

Create a ClickRuntime automation: every Monday at 9am, generate 3 square images for this week's topics (spring sale, new hiking boots, customer story) in flat pastel illustration style, and email me the links.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A small ecommerce brand needs fresh social graphics every week: seasonal backgrounds, product mood boards, blog header images. A designer is expensive for this volume and stock photos look generic, so images get made by hand in an AI tool only when someone finds the time, which is rarely. Posting slows down, and the visuals that do go out are rushed.

On a weekly schedule, your prompts are taken from a list you maintain, or sent to your link by a form or another tool, and each prompt is passed to OpenAI's image generation. The resulting pictures are stored and links to them are emailed to you, ready to review, download and use in your content calendar.

It suits marketers, bloggers, newsletter writers and anyone who needs a steady supply of illustrations.

What you get out of it

A weekly supply of visuals without effort
New images appear on schedule, which keeps posts, newsletters and blog articles supplied with graphics. You spend your time choosing the best ones instead of generating them one at a time.
Consistent style through shared prompts
Because each image comes from a prompt you control, you can keep wording about colors, lighting and composition the same. The result is a more recognizable look across the whole feed.
Cheaper than commissioning each image
Generating a batch through the API costs a few cents per image on your own OpenAI account. For routine graphics, that is much lower than buying custom artwork for every post.
Prompts can come from anywhere
A teammate can send a prompt through a form, and a script can send many at once. That makes generation a shared service for the team, not a task that depends on one person.
Images are kept, not lost
Stored images and links in your inbox mean a good result is not lost when a browser tab closes. You can find an old image by searching the email for the prompt.

How it works

What happens, step by step

Every week, ClickRuntime takes your list of planned topics and turns each one into an image prompt in your chosen style.
It asks OpenAI to create an image for each prompt.
You get one email with each topic and a link to its image, ready for your social posts.

Before it runs live

Connect OpenAI

What you get

RunsWeekly

Generate weekly social images with OpenAItoday, 9:00Succeeded

Email · This week's imagesspring sale: https://oaidalleapiprodscus.blob.core.windows.net/private/…/img-3Fh2.png

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Run it at a different time, more or less often, or only on weekdays
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other OpenAI steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

generate_images_from_prompts_dall_e_gpt_image.pyexample

from clickruntime import on_trigger, credentials, http, notify

TOPICS = ["spring sale", "new hiking boots", "customer story"]
STYLE = "flat pastel illustration, simple shapes, soft colours, no text"

@on_trigger
def run(event):
    headers = {"Authorization": f"Bearer {credentials.secret('OPENAI_API_KEY')}"}
    lines = []
    for topic in TOPICS:
        resp = http.post("https://api.openai.com/v1/images/generations", headers=headers, timeout=120, json={
            "model": "dall-e-3", "prompt": f"{topic}, {STYLE}", "size": "1024x1024", "n": 1})
        resp.raise_for_status()
        lines.append(f"{topic}:\n{resp.json()['data'][0]['url']}")
    notify.email_me("This week's images (links expire in 1 hour)", "\n\n".join(lines))
    return {"images": len(lines)}

FAQ

Common questions

Which image model does it use?

It calls OpenAI's image generation API, which offers DALL-E and the newer GPT Image models. You choose the model and the size when you set it up, and billing goes to your own OpenAI account using your API key.

Can I use the images commercially?

OpenAI's terms generally let you use images you generate, including commercially, but you should read the current terms and any restrictions that apply. Check that prompts avoid trademarked characters or real people's likenesses. Prompts that name a specific brand or a real person are the ones most likely to be declined, so keep them generic.

What happens if a prompt is rejected?

OpenAI's safety checks can refuse some prompts. In that case, the run records the refusal for that prompt, continues with the others, and the email notes which prompt failed so you can reword it. Reviewing every generated image before posting remains a sensible step, and you can ask for the original size.

What permissions does it need?

API key (All, or Restricted with image access). Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's AI allowance.

How many runs does it use?

One run each time it runs (weekly). Checks that find nothing to do and stop right away aren't counted.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

On a schedule