Skip to main content

Get Support
Have a question? Let's get you an answer!

How Do I...? Troubleshooting Code & Webhooks Developer Zone

Other Help Resources
Wait, there's more! Check out these Community sourced spaces for additional resources.

Zapier Help Center Hire an Expert

Learning Resources
All of our best learning resources can be found here.

Featured Articles Show & Tell Zapier's products AI Hub Zapier Tools Hub

Share your knowledge
Give back to the Community by sharing your automation wins and helping to answer questions.

Share your success See unanswered questions User Groups

Other Learning Resources
Some of our favorite additional ways to upskill your Zapier knowledge.

Zapier Learn Zapier Blog Zapier Webinars

Product Updates
Check out what is new and upcoming with Zapier with our regular product updates.

Product Updates

Early Access Program
Want to join Early Access? Learn more here.

  • Home
  • Get Help
  • How Do I
  • How do I use ChatGPT to generate images and save them with descriptions to Google Drive in Zapier?

Hi, 
I’m trying to decipher what’s the best way to use ChatGPT (Web version, not their API as the quality of generations is better) to generate images and save to Google Drive. The best I got was to use “Actions” https://actions.zapier.com/gpt/actions/ with the help of this youtube tutorial but I’m stuck.

It doesn’t upload the actual image but a txt file with a brief description. 

My preferred scenario would be to:
1. Generate an image with Custom GPT
2. Save it to my drive​​​​​​
3. Save the prompt / description created by ChatGPT as well.

Any ideas?
thanks

Welcome, @Andrzej. Thanks for joining the Community! 🎉

Can you share a screenshot showing the set up of the Zapier AI action for the GPT that’s uploading the image to Google Drive?

If it’s saving the image as a txt file my guess is that there may be a slight issue with the setup of that AI action which is causing that incorrect behaviour. So I’d just like to double-check the setup to see if that’s the case. Please remove/hide any private information (like names, emails, addresses etc.) from any screenshots before sharing.
 

Thanks for your assistance, looking forward to hearing from you! 🙂

Hi @SamB , maybe I’m doing something wrong or the system is still not perfect. I feel like every time I try it I get a different result (either an error, or questions from GPT how to name the file, or some error txt file in my Drive).
Also the whole process requires to confirm actions manually a few times… so that kind of beats the purpose of automating things. Still, I would like to try if it works somehow. 

Thank you for trying to help out. 

Attached are 3 screenshots and here’s are the instructions I used:
 

Create images for the user and next follow the instructions.
====
This GPT, named Zapier Test, is designed to assist users with integrating Zapier actions, specifically for uploading files to Google Drive. It should provide detailed assistance for configuring and troubleshooting Zapier automations. The GPT must inform users that they need to reply after the action completes to continue. If the user has confirmed that they've logged into Zapier's AI Actions, the GPT should start by checking if the necessary Zapier AI Actions are available for their request. If an action is not available, the GPT will provide the user with a configuration link and instructions to enable the action. Once the user has configured the required action, the GPT will proceed with the original request. When handling file uploads, the GPT will provide the URL of the generated image for the user to input into the Zapier configuration. The GPT should remind users to select the image file or binary data as input for the 'File' field in their Google Drive upload action. 


###Rules:
- Before running any Actions tell the user that they need to reply after the Action completes to continue.
- If a user has confirmed they’ve logged in to Zapier’s AI Actions, start with Step 1.

###Instructions for Zapier Custom Action:
Step 1. Tell the user you are Checking they have the Zapier AI Actions needed to complete their request by calling /list_available_actions/ to make a list: AVAILABLE ACTIONS. Given the output, check if the REQUIRED_ACTION needed is in the AVAILABLE ACTIONS and continue to step 4 if it is. If not, continue to step 2.
Step 2. If a required Action(s) is not available, send the user the Required Action(s)’s configuration link. Tell them to let you know when they’ve enabled the Zapier AI Action.
Step 3. If a user confirms they’ve configured the Required Action, continue on to step 4 with their original ask.
Step 4. Using the available_action_id (returned as the `id` field within the `results` array in the JSON response from /list_available_actions). Fill in the strings needed for the run_action operation. Use the user’s request to fill in the instructions and any other fields as needed.
REQUIRED_ACTIONS:
- Action: GDrive_Upload
{available_action_id}: 01HP5CV...here is the id...NW

 

Thanks for sending over those instructions and screenshots @Andrzej! 🙂

Hmm, looking at the set up of the Google Drive: Upload Drive AI action, it appears that you’ve set it to not include a value for most of the fields. And for the File field it would be expecting a value to be select within the AI action set up window, not provided by the GPT: 
06afc8ca439c4b88604d0a68a770cd33.png

So I think that might be what’s causing some of the issues here. For the File and File Name fields at least, I’d suggest changing the current settings to “Have AI guess a value for this field” instead. That way it’ll be expecting the GPT to provide the file and it’s name. You can learn more about whether fields should or shouldn’t be set to have AI guess it’s value here: Decide if AI should guess the value of a specific field in AI actions
 

Can you give those changes a try and see if that helps get it working more consistently?

Terms & Conditions