Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
vunderba
12 days ago
|
parent
|
context
|
favorite
| on:
FLUX 3 Image
Yeah, given how much better Ideogram v4 outputs are when you use the proper structured JSON (background, elements, etc.) I think most users probably have stuck some kind of Qwen/Gemma-based LLM between their raw prompt and the CLIP encoder.
help
Consider applying for YC's Winter 2027 batch!
Applications
are open till November 2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
