points by gavmor 1 day ago | 0 comments
Images without prompts and statistics are... meaningless. We don't know if/how these adhere, whether they took a thousand hours or a thousandth of a second.
> “Would you tell me, please, which way I ought to go from here?”
> “That depends a good deal on where you want to get to,” said the Cat.
> “I don’t much care where—” said Alice.
> “Then it doesn’t matter which way you walk,” said the Cat.
(Lewis Carroll)
[–] echelon 1 day ago
These are not meaningless.
If you do regular image gen, you can see that these images demonstrate memorized styles, broken anatomy, bad text layout (or hallucinated text), etc. Even the old Dall-E watermark is a throwback.
Generation times are orthogonal.
[–] dahart 1 day ago
I don’t do image gen regularly… so I’d love more context. I can see some less good features in the images but I’m not fluent with what today’s generators would do. I agree with GP that it would be quite useful to know about the prompts & iteration effort. If generation times changed, they could be relevant & helpful.
[–] gavmor 1 day ago
I don't do extremely regular image gen, but I've been running ComfyUI on my 3090 for, jeeze, two years?
Here's my homelab blog: https://www.gavmor.com/regular-labs/
Maybe I'm just not that observant, but all these pictures are just... "LGTM."
When I'm generating, I have really specific adherence/performance goals.
[–] thecodebeats 1 day ago
This quickly escalated from nostalgia to ComfyUI image optimization
[–] thenthenthen 1 day ago
[–] Imustaskforhelp 1 day ago
[–] thenthenthen 1 day ago
[–] doubled112 23 hours ago