barty777
Joined 6 years ago
Joined 6 years ago
How many times have combed through 5 different websites trying to find some image/icon/visual with transparent background only to find the background isn't really transparent, it has a watermark, or that you have to pay for a monthly subscription only to get that one asset.
If this sound familiar, we know your struggle. This is why we created MagicStock, a single website where you can generate any kind of image/icon/illustration/visual with transparent background, by just describing what you want.
Goal of this tool is to become a simpler and cheaper alternative for tens of different websites where you search for various kinds of graphic and design assets like icons, illustrations, vectors, product photos...
We just released a beta version of MagicStock and we would love to hear from you folks if this looks interesting. It's still nowhere near perfect, but we hope it can still be useful to some of you even at this early stage.
Any kind of feedback is most welcome
Sounds interesting? Give it a go here -> https://aimages.ai/MagicStock
We are introducing AImages, the simplest and the fastest way to restore and enhance your videos.
To use AImages, you only need a web browser. Simply upload video, choose AI enhancement filters, and chill out while we enhance your videos.
Some of the enhancement and restoration filters we currently support:
* Up to 4X, AI powered resolution upscaling
* Video noise reduction
* Video compression artifacts removal
* Tape Prettify - enhance the look of old video tape formats (VHS, Beta…)
We have just released a public Beta which you can try for free: https://app.beta.aimages.ai
As this is still a beta product, we would love to hear your feedback on how we can improve the AImages platform.
Automated photo tagging seems like a good idea and we will certainly think about it more.
Babbly is one of our side projects we have been developing for the past few months. Our team has a lot of expertise in Computer Vision and we have always wanted to test if in-the-cloud real-time inference is possible with AI. Babbly can process up to 5 pictures per second which demonstrates this approach is more than viable. The main advantages of the in-cloud model are seamless AI model updates, reduced battery consumption, and much lower restrictions on the model size which results in better accuracy.
The model was trained on ImageNet and OpenImages public datasets which are not perfect for this kind of computer vision task, so the accuracy is not stellar. We plan to work on this issue in the future :)
We realize this app doesn't offer much feature-wise, but we think any form of fun/knowledge can be helpful during this pandemic. And yeah, any kind of feedback is more than welcome :)