remixtures, to ai Portuguese
@remixtures@tldr.nettime.org avatar

#AI #GenerativeAI #AITraining #Chatbots: "ChatGPT and other AI-powered bots may soon be "running out of text in the universe" that trains them to know what to say, an artificial intelligence expert and professor at the University of California, Berkeley says.

Stuart Russell said that the technology that hoovers up mountains of text to train artificial intelligence bots like ChatGPT is "starting to hit a brick wall." In other words, there's only so much digital text for these bots to ingest, he told an interviewer last week from the International Telecommunication Union, a UN communications agency.

This may impact the way generative AI developers collect data and train their technologies in the coming years, but Russell still thinks AI will replace humans in many jobs that he characterized in the interview as "language in, language out.""

https://www.businessinsider.com/ai-could-run-out-text-train-chatbots-chatgpt-llm-2023-7

cragsand, (edited ) to ai

I learned how to train LoRa AI models using open source StableDiffusion...

For the purpose of recreating the appearance of my 3D VR roleplaying character the results I got were amazingly good... almost frighteningly so.

I'll go through the process, results and some thoughts.

🧵 part 1of4

cragsand, (edited )

So much of the majority of AI art I see is terrible, bad looking and deformed. But with the right instruction's it doesn't have to be.

To accurately create fictional characters, this is probably the best method I've seen so far. There's work involved for training a model like this and not something you can just give a bunch of prompts and expect good results.

I started by gathering 64 screenshots of my 3D VRChat model from Blender in various positions and angles in different lighting while wearing select clothing of choice. Then I added proper tags describing each image in a respective text file.

Based on the training data and they keywords I specified, you can input various clothing alternatives including:

  • armor
  • jacket
  • shirt
  • barechest
    Training took about 30 minutes using an RTX2080Ti GPU.

#stablediffusion #loramodel #characterart #ai #aiart #aitraining #sd #lora #tech #technews #vr #3d #vrchat #roleplay #neondivide #wasteland

cragsand, (edited )

These guides were really useful for explaining complex concepts without having the understanding of the mathematics involved. It tends to get really complicated the deeper you delve into it.
https://rentry.org/lora_train
https://rentry.org/59xed3

The GUI for stable diffusion I'm using is completely open source written in Python for everyone to use https://github.com/AUTOMATIC1111/stable-diffusion-webui

I posted the LoRa AI training model publicly for download here for anyone curious: https://civitai.com/models/70408/cragsand-character-lora-sten-berglund

Since I really liked the results I ended retouching some parts manually. Things like eye color, fingers and random clutter where there were details that looked weird.

The end results are available in this gallery here: https://www.deviantart.com/cragsand/gallery/87722291/sten-berglund-character-artwork

#stablediffusion #loramodel #characterart #ai #aiart #aitraining #sd #lora #tech #technews #vr #3d #vrchat #roleplay #neondivide #gunsmith

cragsand, (edited )

End thoughts...

With this technology gaining traction I certainly sympathize with artists concerned about their profession being in danger. It's a topic worth discussing and what it's societal effects will be. I can certainly see it ending up being bad and requiring proper regulation.

One thought on my mind would be that these are "tools" for us to use, and as with any tools if they're good or bad ends up being determined by how they're used. It's not the technology itself that is the danger, but rather how corporations and bad interests may exploit it to the detriment of everyone else.

Curious to hear other's thoughts about this and how we can approach it in a way that is beneficial for everyone.

Thank you for reading the thread ! 💙

#stablediffusion #loramodel #characterart #ai #aiart #aitraining #sd #lora #tech #technews #vr #3d #vrchat #roleplay #neondivide #wasteland

j3j5, to random
@j3j5@hachyderm.io avatar

So, tell me again why indie devs shouldn't build anything related to search/scraping on the fediverse? Google's already scraping the hell out of us, we're just giving them the service on a silver platter

#Google #AI #AITraining #FediSearch #FediDev

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