Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
halJordan
24 days ago
|
parent
|
context
|
favorite
| on:
Qwen-Image: Crafting with native text rendering
If you think diffusing legible, precise text from pure noise is garbage then wtf are you doing here. The arrogance of the it crowd can be staggering at times
bavell
24 days ago
[–]
They're referring to the training data being garbage, not the diffusion process.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: