zlacker

[return to "Imagen, a text-to-image diffusion model"]
1. manchm+F5[view] [source] 2022-05-23 21:22:47
>>kevema+(OP)
The big thing I’m noticing over DALL-E is that it seems to be better at relative positioning. In a MKBHD video about DALLE it would get the elements but not always in the right order. I know google curated some specific images but it seems to be doing a better job there.
◧◩
2. benwik+77[view] [source] 2022-05-23 21:30:39
>>manchm+F5
Totally—Imagen seems better at composition and relative positioning and text, while DALL-E seems better at lighting, backgrounds, and general artistry.
◧◩◪
3. kossTK+7o[view] [source] 2022-05-23 23:18:26
>>benwik+77
Yeah Dall-e looks amazing, to a mysterious degree even with hints of humour and irony, while imagen images look cheap, one dimensional and quite ugly to be honest.

Still amazing that we're at a point where that's the case, they're both incredible developments.

[go to top]