Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
zimpenfish
on May 24, 2022
|
parent
|
context
|
favorite
| on:
Imagen, a text-to-image diffusion model
The latent-diffusion[1] one I've been playing with is not terrible at drawing legible text but generally awful at actually drawing the text you want (cf. [2]) (or drawing text when you don't want any.)
[1]
https://github.com/CompVis/latent-diffusion.git
[2]
https://imgur.com/a/Sl8YVD5
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
[1] https://github.com/CompVis/latent-diffusion.git [2] https://imgur.com/a/Sl8YVD5