Hi , is there an alghoritm that may function on a phone for image GenAI ( like Dall-e 1 ) ? Ok , I'll explain better : my idea is that the user gives files for training to the AI and then these data will be saved in a TinyDB . But after that , how to generate an image ? Modern GenAI image systems are too complex and expensive for a phone , so I guess I'll need a new one to make this ... app . I know there are VAE's , GAN's , Diffusion Models and combinations of these ... ( if you know some more please say to me because I think allready know all of these possible alghoritms ) . Anyway , this systems are too complex fore a Smartphone and for App Inventor .
So ... what can be an alternative alghoritm ?
I don't guess the majority of you will reply : is complex .
Anyway ... thanks in advance , even more now because of the complexity of the question
I tought this would be more interesting , but I think is OK if are just 4 days from the last post , that are a small amount of time ...
OK I guess this will be lost ... or hidden ... and I'll find alternatives myself
I think that will be a cool thing to do but I don’t know anything about ai so sorry I cant help you.
are you meaning for the AI to make one image from multiple files or not. if so I have code that theoretically works but I wont know till tomorrow.
Is it a code that generates images offline ?
if you can use the MIT image bot offline then yes
I can send you the code if you want
Sorry but that component works just online with OpenAI's API
OK well I can still send the code and you can test it out
Ok I can anyway look if can help me
Ok thanks
welcome
Sorry users to desturb but I am having some problems to "translate" the GANs ( Generative Advertisal Nets ) formula to App Inventor blocks ( For example , how to insert min and max ? )
Any help is welcome
Thanks
P.S. : Would be very helpful a blocks' screenshot / image ...
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.