Hi @lavista, will check the videos and try the 16:9 size, good tips ! and yeah, i won't expand on it but definetely AI recognition process in Healthcare is a big leap forward. Tons of improvement everyday,

Hi @castleberry, Your post is a great synthesis of the state of the art so far. What a work and artwork ! It clearly demonstrates the added value an artist can bring when you just give him new tools, bringing

A big thank you for this ! I will check this. I overlooked these possibilities when i was learning colab with unique focus on natural langage.

By experience i would say that the prompt is the main driver of the algorithm attention. If you don't modify it, each run will be 'similar' but not the same. Seed is made to reproduce the exact same result.

I have to admit i had some passion last year for GPT-2, but it's outdated now...

Hi @juecoree, indeed there is surprising coherence in all your pictures and i sometimes share the same feeling altough technically every run should start from clean parameters... One question : do you

I did not know it could come from the language model, but that would indeed make sense. Lower repetition and keeping focus on a topic is a general problematic in GPT-n technology. In case of text only

I know the book but i never had the opportunity nor to see the film nor to read the book completely, but yes, if you think of it, dolphins and whales are symbols widely spread everywhere. And then this

Just joined. Thank you.

@jotakrevs, thanks for the mentions. And congratulations for the work spent on this challenging issue with faces. I will have to study your findings... But anyway, it looks like you greatly succeed to

Hi @castleberry, Here a poor translation of the whole legend as reported in the book In the beginning the Great Spirit slept in nothing. His sleep lasted for eternity. And then suddenly, no one knows why,

Hi @jotakrevs, @kaliyuga, @castleberry, @lavista ... Maybe you already knew but i just found this playground :

Thank you @curangel and @nikv for your support and mention.

I feel proud and honored. Thank you for the mentions and the attention from the community.

Hi @lavista, cool post and pictures. I find the 16:9 especially polished. Usually free colab and K80 should support 640X480 size (with VQGAN at least). Number of iterations should not influence memory

Thx for your answer. I think we are indeed aligned. If i find alternative useful resources, i'll share it.

I agree, posting is not commercial use, there is no real trade, it's the post that is rewarded. This is not claiming copyright ownership... Oh Clip-guided Diffusion ... did you succeed to get some results

Thank you !

law is made to be broken ;-)

Thx @kaliyuga. forewarned is forearmed... A question : Didn't you train your own model ? If so, i may imagine that if you can craft a dataset with pure public domain picture and collect all credits in