DavidMarzalC, to Symfony Spanish
@DavidMarzalC@mastodon.escepticos.es avatar

Encaramos el final de marzo con otro nuevo episodio de "Accesibilidad con Tecnologías libres", para los amigues.

En https://accesibilidadtl.gitlab.io/05 tenéis las notas del programa con los temas tratados y los enlaces.

Si seguís a este alias @6706483 , tendréis automáticamente las publicaciones del podcast dentro del Fediverso

Y por si aún no lo tenéis el feed RSS para vuestras aplicaciones es:
https://accesibilidadtl.gitlab.io/feed

En este episodio 05 participan entre otras personas:

Esperamos que os resulte interesante.

joe, to random
@joe@toot.works avatar

I just updated https://jws.dev: I added MacGPT, Ollamac, and Ollama Web UI to the Resources page

joe,
@joe@toot.works avatar

It looks like llava does a much better job of describing photos.

ErikJonker, to ai
@ErikJonker@mastodon.social avatar

If true and replicated this offline (!) and opensource LLaVa model on a raspberry Pi is very impressive.

devinprater, to ai

Well, I'm sure an NVDA addon with this will be here soon. Just amazing how far things have come. I mean, I hope there's a Windows version of the Llava part of this anyway.

llamafile is the new best way to run a LLM on your own computer:

https://simonwillison.net/2023/Nov/29/llamafile/

devinprater, to ai

Welp, here we go. Be My Eyes is so great, people are just... Calling their projects Be My Eyes web apps now. Cause it's 2023 and here we are. No, I haven't tried this thing. I hope it's worth the absolute shitstorm of a hype train this will cause in the blind community once people get to looking at it.

https://github.com/lxe/llavavision

aaronjohn0412, to milan
@aaronjohn0412@tweesecake.social avatar

Here is a photo of me taken in front of cathedral that I've ask LLaVA to describe for me. to my sighted friends, I'll appreciate you giving feedback on its accuracy.

Description:
The image features a man wearing a pink shirt standing in front of a large, ornate building with a blue sky in the background. The building appears to be a cathedral, as it has a tall structure and a prominent clock tower. The man is holding a camera, possibly taking a picture of the impressive building.
There are several other people in the scene, some of them closer to the foreground and others further in the background. They seem to be enjoying their time near the cathedral, possibly admiring its architecture or taking photos as well.

aaronjohn0412, (edited ) to EyeHealth
@aaronjohn0412@tweesecake.social avatar

for those who need descriptions or for photos, here is a model that pretty much does it. It is called . I will post a sample image with a description on my next post and let you sighted friends comment on it. 😁

https://llava.hliu.cc/

Jason, to ai

I took a quick look at the new AI model, to see how it handled descriptions of historic artworks.

https://www.linkedin.com/pulse/first-look-llava-ai-jason-evans

  • All
  • Subscribed
  • Moderated
  • Favorites
  • normalnudes
  • rosin
  • ngwrru68w68
  • GTA5RPClips
  • DreamBathrooms
  • mdbf
  • magazineikmin
  • thenastyranch
  • Youngstown
  • Durango
  • slotface
  • everett
  • vwfavf
  • kavyap
  • megavids
  • Leos
  • khanakhh
  • cisconetworking
  • cubers
  • InstantRegret
  • ethstaker
  • osvaldo12
  • modclub
  • anitta
  • provamag3
  • tacticalgear
  • tester
  • JUstTest
  • All magazines