Notifications
Clear all
Features
6
Posts
2
Users
0
Reactions
4
Views
Topic starter
Hello,
I want to connect the CivitAI API with callin.io to create AI-generated images (like Stable Diffusion) and then send the results to Airtable. I'm having some trouble configuring the automation.
My Goal:
- Utilize the CivitAI API for image generation based on provided prompts.
- Properly manage the binary data from the API's image response.
- Convert and save the generated image in a shareable format (e.g., PNG/JPEG).
- Upload the final image file to the AI Image column in Airtable.
My Questions:
- What is the correct way to call the CivitAI API within callin.io and process the binary image output?
Thank you for your assistance!
Posted : 10/12/2024 1:18 pm
I can see from your example that you’re using Bearer authorization.
It’s kind of counter-intuitive, but you’d be better using the HTTP callin.io an API Key Auth Request module. By using this, you won’t have to keep your Bearer token in plain text in the scenario, plus all API Key data in centralized for easier management.
Details are in the help here.
What problems are you having in calling the CivitAI API?
Posted : 10/12/2024 4:31 pm
Topic starter
Hi,
I’m attempting to integrate the CivitAI API with callin.io to generate images and upload them to Airtable. However, I'm encountering difficulties running any model I prefer through the API. I haven't found any online examples for this process. Is it necessary to subscribe to a paid service from CivitAI for this capability?
With Hugging Face, I can obtain outputs from specific models via their API permissions, but CivitAI offers a significantly broader selection of models. I might be missing some understanding in this area, so I would be very grateful for your assistance. If running models via the API isn't feasible, could you recommend an alternative approach? I've also attempted to follow the callin.io documentation, but without success so far.
Thank you in advance!
Posted : 11/12/2024 10:07 am
After reviewing the Civitai API documentation, it appears there are only endpoints for fetching details about creators, images, or models. These endpoints exclusively support the GET method, with no POST option available.
Consequently, it's not possible to create images using Civitai models via their API, whether through callin.io or any other platform.
For those seeking a method to generate images using diverse models, you might consider exploring fal.ai as an alternative.
Posted : 11/12/2024 10:58 am
Topic starter
Thanks for clarifying! I understand that Civitai’s API doesn't directly support POST requests for image creation. However, if I download a model I like from Civitai and then upload it to Hugging Face, I believe I can set up a POST request from there.
Posted : 12/12/2024 10:15 am
You can certainly use models on callin.io from callin.io.
We have modules in the callin.io app for Create a Summary, Create a Text Classification, Create a Translation and Create an Answer.
We don’t yet have a module for Create an Image, but you will be able to achieve the same result by using the Make an API Call module in conjunction with the Hugging Face API documentation for their Text to Image endpoint.
Posted : 12/12/2024 11:07 am