HackerTrans
TopNewTrendsCommentsPastAskShowJobs

latentdeepspace

no profile record

Submissions

Show HN: Generate Images in Seconds, Without Limits, One Purchase

image-gen.com
3 points·by latentdeepspace·há 2 anos·4 comments

Show HN: Live Transcription with Whisper in a client-server setup

github.com
2 points·by latentdeepspace·há 3 anos·0 comments

Ask HN: What is the best option to host a low-traffic RestAPI with SQLite

6 points·by latentdeepspace·há 3 anos·7 comments

Show HN: Usage-Tracker.nvim Neovim Plugin

github.com
2 points·by latentdeepspace·há 3 anos·0 comments

Show HN: Prometh-Review an AI PR-Reviewer Companion (In the Command Line)

github.com
1 points·by latentdeepspace·há 3 anos·0 comments

Do Foundation Model Providers Comply with the EU AI Act?

crfm.stanford.edu
72 points·by latentdeepspace·há 3 anos·69 comments

Show HN: Conversational GPT cost estimation tool and writeup

gpt-calculator.gaborvecsei.com
4 points·by latentdeepspace·há 3 anos·0 comments

comments

latentdeepspace
·há 2 anos·discuss
You are getting the code that is required to generate the images which you can use with Google Colab (as you can get free GPUs there). About the models you can use: literally any model (base model, LoRA) can be used, as these are handled automatically (you only need a download link from CivitAI or Huggingface or anywhere else)

Thank you for the input, I'll make sure to change these to make it more clear.
latentdeepspace
·há 2 anos·discuss
If it fits your use case then it's great, but if you want to have more custom generations then you are limited with it.
latentdeepspace
·há 2 anos·discuss
Where do you run the ads? And how did you set it up - how specific your targeting is?
latentdeepspace
·há 2 anos·discuss
Can someone provide a bit of background how the crawling part works?
latentdeepspace
·há 3 anos·discuss
I implemented a dummy real-time (tested on Mac M1) transcription approach with Whisper. You can find the project here: https://github.com/gaborvecsei/whisper-live-transcription

The idea was to provide transcription results as fast as you can, and you can refine it along the way by providing more and more context.