[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/ic/ - Artwork/Critique

Search:


View post   

>> No.6232812 [View]
File: 7 KB, 225x225, 1603535671019.jpg [View same] [iqdb] [saucenao] [google]
6232812

>>6232064
>>6232082
>>6232283
>>6232305
>>6232310


>In fact, the size of the stable diffusion model is only a couple of gigabytes, while it is trained on hundreds of terabytes of source images. In the words of Stability AI CEO and founder Emad Mostaque, this is the collective imagery of humanity compressed into files a few gigabytes big. This immensely lossy compression from the source image to the model, which reduces the volume of data by at least four orders of magnitude, implies that the probability for stable diffusion faithfully memorizing ‘substantial’ parts of specific works of art is extremely slim.

So much for a "mind"

>> No.6232808 [DELETED]  [View]
File: 7 KB, 225x225, 1603535671019.jpg [View same] [iqdb] [saucenao] [google]
6232808

>In fact, the size of the stable diffusion model is only a couple of gigabytes, while it is trained on hundreds of terabytes of source images. In the words of Stability AI CEO and founder Emad Mostaque, this is the collective imagery of humanity compressed into files a few gigabytes big. This immensely lossy compression from the source image to the model, which reduces the volume of data by at least four orders of magnitude, implies that the probability for stable diffusion faithfully memorizing ‘substantial’ parts of specific works of art is extremely slim.

So much for a "mind"

>> No.6232807 [DELETED]  [View]
File: 7 KB, 225x225, 1603535671019.jpg [View same] [iqdb] [saucenao] [google]
6232807

>>6232064
>>6232283
>>6232310
" In fact, the size of the stable diffusion model is only a couple of gigabytes, while it is trained on hundreds of terabytes of source images. In the words of Stability AI CEO and founder Emad Mostaque, this is the collective imagery of humanity compressed into files a few gigabytes big. This immensely lossy compression from the source image to the model, which reduces the volume of data by at least four orders of magnitude, implies that the probability for stable diffusion faithfully memorizing ‘substantial’ parts of specific works of art is extremely slim."

So much for a "brain"

>> No.6185849 [View]
File: 7 KB, 225x225, 1603535671019.jpg [View same] [iqdb] [saucenao] [google]
6185849

>>6181735
post 6 month progress

Navigation
View posts[+24][+48][+96]