Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
bertdb
on Jan 24, 2024
|
parent
|
context
|
favorite
| on:
Direct pixel-space megapixel image generation with...
Did you do any inpainting experiments? I can imagine a pixel-space diffusion model to be better at it than one with a latent auto-encoder.
stefanbaumann
on Jan 24, 2024
[–]
Not yet, we focused on the architecture for this paper. I totally agree with you though - pixel space is generally less limiting than a latent space for diffusion, so we would expect good performance inpainting behavior and other editing tasks.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: