zlacker

[return to "Imagen, a text-to-image diffusion model"]
◧
1. benwik+L6[view] [source] 2022-05-23 21:29:19
>>kevema+(OP)
Would be fascinated to see the DALL-E output for the same prompts as the ones used in this paper. If you've got DALL-E access and can try a few, please put links as replies!
◧◩
2. joeyco+Pf[view] [source] 2022-05-23 22:19:12
>>benwik+L6
Posting a few comparisons here.

https://twitter.com/joeyliaw/status/1528856081476116480?s=21...

◧◩◪
3. rg111+i01[view] [source] 2022-05-24 05:44:26
>>joeyco+Pf
Imagen seems more realistic where Dall-E2 is more feel-good.

That is what I feel personally.

◧◩◪◨
4. joeyco+s41[view] [source] 2022-05-24 06:28:24
>>rg111+i01
I agree with you, but for me, Dall·E 2 feels good because 90% of the time I can keep hitting the generate button and massage the prompt until I get something inspirational, surprisingly, or visually pleasing. Without access to Imagen, it's impossible for me to compare how much of the "realistic feels" of its images is constrained by the taste of the cherry-pickers.
[go to top]