Daily

Generate fresh model output every morning

Each day a new result from the model and prompt you chose lands in your inbox as a link.

Runs: Daily
Apps: Replicate
AI: Not needed
Access: API key

Send this to your assistant

Create a ClickRuntime automation: every day at 8am, run black-forest-labs/flux-schnell on Replicate with the prompt "a calm watercolor landscape, morning light" and email me the image link.

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

People who use Replicate to generate images, music or short videos often want something fresh on a routine: a daily image for a newsletter header, a morning social media graphic, a prompt they like to run each day to see how a model behaves. Doing it manually means opening the site, pasting the prompt, waiting and saving the result, which turns a good idea into a chore.

Every morning at the time you choose, ClickRuntime starts a Replicate prediction with your prompt and the model you picked. It asks Replicate to wait for the result and checks again if the job is not done, then emails you a link to the generated output so it is waiting in your inbox when you start work.

Creators, marketers and hobbyists with a repeating creative task will find it saves the same small effort every day.

What you get out of it

Fresh creative material every day
An image or clip arrives without you having to remember to ask. For a daily newsletter or a content calendar, that removes the blank-page moment from the start of the day.
Model behavior can be tracked
Running the same prompt daily shows how a model performs over time, and when its version changes. People who care about output quality can notice a drift or an improvement early.
Your prompt is saved and reused
Once the prompt works well, it runs the same way every time. You avoid rewriting it, losing track of the version that gave the best results, or changing it by accident.
Cost stays predictable
One prediction per day is easy to budget for. You know your spend on this task in advance, and you can switch to a cheaper model if the numbers add up.
Output reaches you where you work
The email contains the link, so the image can go straight into a draft or a chat. There is no extra visit to the Replicate website to download the file.

How it works

What happens, step by step

Every morning, ClickRuntime sends your saved prompt, such as a calm watercolor landscape, to the image model you chose on Replicate.
It waits for Replicate to finish the image.
You get an email with the prompt and a link to today's image. If the run fails, the email gives the error instead.

Before it runs live

Connect Replicate

What you get

RunsDaily

Generate fresh model output every morningtoday, 9:00Succeeded

Email · Today's imagea calm watercolor landscape, morning light https://replicate.delivery/xezq/out-0.webp

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 Replicate 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.

scheduled_generation_run.pyexample

import time
from clickruntime import on_trigger, credentials, notify, http

PROMPT = "a calm watercolor landscape, morning light"

@on_trigger
def run(event):
    headers = {"Authorization": f"Bearer {credentials.secret('REPLICATE_API_TOKEN')}", "Prefer": "wait"}
    p = http.post("https://api.replicate.com/v1/models/black-forest-labs/flux-schnell/predictions",
                  headers=headers, json={"input": {"prompt": PROMPT}}, timeout=70).json()
    while p["status"] in ("starting", "processing"):
        time.sleep(3)
        p = http.get(p["urls"]["get"], headers=headers).json()
    if p["status"] != "succeeded":
        notify.email_me("Replicate run failed", f"{p['id']}: {p.get('error')}")
        return {"status": p["status"]}
    notify.email_me("Today's image", f"{PROMPT}\n{p['output'][0]}")
    return {"image": p["output"][0]}

FAQ

Common questions

Does it wait for the image to finish generating?

Yes. It sends the request with a Prefer: wait header, which lets Replicate hold the response for a short time until the result is ready. If the model takes longer, the run checks the prediction status again until it completes or fails.

Can the prompt change each day?

It can. The prompt may include the date, or be picked from a list in rotation, so each day produces something different. Without any variation, the same prompt will give similar results unless the model uses a random seed.

How long are the generated files available?

Replicate keeps output files for a limited period, commonly around an hour for API output delivered by URL. If you want to keep an image, download it soon after the email arrives, or ask for it to be saved to storage you own.

What permissions does it need?

API key. 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 (daily). 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.

Daily