Are you guys thinking about implementing a chrome extension with Visionati so that way I can just look at a image on Pinterest, Google, or Amazon, and I can point and click and it will describe what I am looking at on the fly rather than going to visionati site all the time
A: Yes it does, the API supports OCR specifically. Our front-end exposes it through the normal prompt based services, where you would just use a custom prompt like "extract the text from this image", in order to extract the text.
Q: Concerns and Considerations Regarding App Limitations and Features
I signed up for testing purposes and purchased 500 credits. Unfortunately, the upload is limited to 10 MB, which means it is not usable for the majority of my images. Ki-images that slightly exceed 10 MB are also not usable here. I find the app very good, but what currently holds me back from making a purchase are the limitations to 10 MB and the lack of a drag-and-drop function.
Someone here had asked if they could edit 40 MP images, and it was answered that the app itself has no limitations, and uploading to OpenAI externally goes smoothly over 10 MP.
My question is whether this will change in the future, or do we have to live with the limitations? I find the possibilities below 10 MB quite amazing; perhaps your answer can convince me to make a purchase.
Q: AI prompt generation
Can i upload a photo or image and then get a prompt that i could use in an AI request to get a similar image generated?
zquestz
Apr 27, 2025A: Yes, Visionati creates excellent image creation prompts.Just use the "prompt" role. 😀
Share Visionati
Q: Chrome extension
Are you guys thinking about implementing a chrome extension with Visionati so that way I can just look at a image on Pinterest, Google, or Amazon, and I can point and click and it will describe what I am looking at on the fly rather than going to visionati site all the time
zquestz
Apr 21, 2025A: Absolutely! In fact it already exists! We are just waiting for approval from the Chrome store. 😀
https://github.com/visionati/visionati-image-scanner
There is also a Firefox extension.
https://addons.mozilla.org/en-US/firefox/addon/visionati-image-scanner/
Share Visionati
Q: Image to Text and Language
Hi
If an image has text on it can I extract the text?
If yes does it support Hebrew?
thanks and good luck
zquestz
Apr 15, 2025A: Yes it does, the API supports OCR specifically. Our front-end exposes it through the normal prompt based services, where you would just use a custom prompt like "extract the text from this image", in order to extract the text.
Yes Hebrew is supported.
Share Visionati
thank you
Q: Concerns and Considerations Regarding App Limitations and Features
I signed up for testing purposes and purchased 500 credits. Unfortunately, the upload is limited to 10 MB, which means it is not usable for the majority of my images.
Ki-images that slightly exceed 10 MB are also not usable here.
I find the app very good, but what currently holds me back from making a purchase are the limitations to 10 MB and the lack of a drag-and-drop function.
Someone here had asked if they could edit 40 MP images, and it was answered that the app itself has no limitations, and uploading to OpenAI externally goes smoothly over 10 MP.
My question is whether this will change in the future, or do we have to live with the limitations?
I find the possibilities below 10 MB quite amazing; perhaps your answer can convince me to make a purchase.
With kind regards,
Klaus
zquestz
Apr 15, 2025A: I went ahead and bumped image upload max to 20MB. This matches the largest files supported by our backends. Hope this helps. =)
Share Visionati
Verified purchaser
Thank you very much, that was quick, and the answer was convincing. I purchased License Tier 2.
Q: Credit usage
How many credits does if take per image and per AI service used per image?
zquestz
Apr 15, 2025A: It is currently 1 credit per description per backend.
Share Visionati
Assuming backend means per platform used so what's that minimum and default? Are they all turned on at once or up to xx many at a time? Thanks
The minimum would be 1. The default is 4 description backends and a couple tagging backends and is 5.
You can adjust the services used on your profile page.