Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nickthegreek
on Jan 31, 2023
|
parent
|
context
|
favorite
| on:
Extracting training data from diffusion models
I imagine reliability means that with the exact prompt, seed, cfg scale, model checkpoint, blah blah and on the same hardware, they can continue to get an image that they consider close enough to the original.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: