←back to thread

Z-Image: Powerful and highly efficient image generation model with 6B parameters

(github.com)
396 points doener | 1 comments | 30 Nov 25 11:36 UTC | HN request time: 0s | source
Show context
GuestFAUniverse ◴[07 Dec 25 04:50 UTC] No.46179244[source]▶
All the examples I tried were garbage. Looked decent -- no horrors -- but didn't do the job.

Anything with "most cultures" were manga-influenced comic strips with kanji. Useless.

replies(1): >>46182468 #
GaggiX ◴[07 Dec 25 15:39 UTC] No.46182468[source]▶
>manga-influenced comic strips with kanji. Useless.

Are you sure it was Japanese? Because the model is Chinese so it's likely to output Chinese (it happened in my testing).

replies(1): >>46183025 #
GuestFAUniverse ◴[07 Dec 25 16:44 UTC] No.46183025[source]▶
Honestly I don't know if it was (Simplified) Chinese, or Japanese Kanji (so, symbols derived from Chinese).

And it isn't even relevant. "most cultures" cannot read anything of it. So what's the nitpicking about?

replies(1): >>46183289 #
1. GaggiX ◴[07 Dec 25 17:17 UTC] No.46183289[source]▶
>So what's the nitpicking about?

Idk I just thought it was funny to read the ignorant comment that called the Chinese model useless because it rendered Chinese text and calling it Japanese. The model is trained to render English or Chinese text.