How AI Creates Images/Videos/Audio - Diffusion Models Explained

[@sreenathgotur]

Thank you for the overview, I got a decent understanding of the high level processing steps involved. Appreciate it.

[@syntax_error6882]

thanks for the video .. i trry to undesrtand something the dataset is made from clean image and noisy image but the model itself its composed by what ??

[@vijaysundharam1218]

Is there a video or tutorial explaining, how to create our own local AI (anything) like, image generator, log analyser, text to text, text to image, video generator as such? Any guidance would be appreciated

[@AdamLucek]

If you're interested in the ground up, Andrej Karpathy's Zero to Hero guide is bar none karpathy.ai/zero-to-hero.html If you're interested in tuning foundational diffusion models more, I just released a video about that! kzbin.info/www/bejne/rGmcnHVqhLiWhaM

[@vijaysundharam1218]

Can't be any easy in understanding this