dome271
No user record in our sample, but dome271 has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
No user record in our sample, but dome271 has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
I also explain more in the video I made about Paella (https://youtu.be/zdE1I6kYKYc). Maybe that clarifies things more.
Fully correct, also the v2 of the paper introduced a model that is bigger and slower, however generates better images. So the 500ms was only for the first model we introduced in v1. I also want to mention our new work…
Yea you can. It's the same as with any other CNN based model that is not forced to have a specific shape (like transformers if they use specific positional embeddings). You can also look at the blog post where different…
that's the correct answer. I love the previous idea posted above, but it was really just that the model was good at food initially and Pablo is from spain, so we decided to name it after same spanish dish. We are…
Hey, (one of the authors here). First of all the blog post is talking about the v1 of the paper, which was extremely fast, but not comparable to SD in any way. The v2 in arxiv is slower and does not achieve 0.5 seconds,…