Damus
macofcrypto · 154w
Natively on device without the use of an API?
Vlady · 154w
Unfortunately, that won't be possible in the next few years. Model data is several Gb in size, and cpu / gpu computation is intensive.
Mark WhatsHisface · 154w
Please sir, my poor phone battery.
Aeontropy · 154w
So the plan is to have SD in Amethyst but as remote connection to colab or something? I'm trying to understand in a less techie term and more in christian term lol
Jimmy · 154w
What do people use for neuraul network libraries on android? Can pytorch be compiled to be used in Kotlin? How about web assembly?
fmar · 154w
Check out tinygrad and what George Hotz is doing with openpilot.
Bayani Mills · 153w
Stable Diffusion? https://huggingface.co/spaces/stabilityai/stable-diffusion
Connie West · 153w
DALLE
DavidAPF · 153w
Con Bing se pueden generar imágenes con IA desde Android usando la aplicación y poniendo tu cuenta
Tartaruga Falida · 153w
As unicas formas que eu encontrei é que os apps de TextDiffusion no android (imagine/wombo) usam dalle mini. Não encontrei nada de pytorch, tensorflow usa apis google. Só deu certo criar uma rootfs uma especie de maquina virtual.
Tartaruga Falida · 153w
https://github.com/EdVince/Stable-Diffusion-NCNN
Tartaruga Falida · 152w
8s in unbuntu andronix 😁😁😁✌️
strg · 11w
Something like PocketPal? https://play.google.com/store/apps/details?id=com.pocketpalai