I think most a lot of image and video models are hybrids of the 2 now, taking advantage of both, like Stable diffusion and Sora
2024-05-14 23:24:32
1
seasd :
Can you use a diffusion model for text?
2024-05-15 01:02:41
1
kobrzut :
Such a great way of explaining these complex concepts!
2024-05-15 17:06:01
1
sam :
your vids are so helpful as this is not my expertise
2024-05-14 23:24:51
2
Vaitkus :
Omg this is very interesting, could you please make some videos on explaining relationship betweet word combinations and image result
2024-05-18 06:54:33
1
Aman Bansil :
Diffusion text is interesting. There’s a paper out that talks about using diffusion models for text. Generating the whole text in one go apparently helps to be contextually relevant (just as an image)
2024-05-17 07:35:29
1
riverranchmt :
Very well explained!
2024-05-14 23:43:42
1
boilerdad24 :
How do these algos actually learn? Is it short term only; ie while the model is trained?
2024-05-15 04:04:54
1
Rybotron :
How do multimodal LLMs work and gen images?
2024-05-15 03:12:28
0
MtnKiddo :
👍👍👍
2024-05-15 15:12:41
2
blue cloud :
GANs or diffusion?
2024-05-15 00:01:03
1
Homer Read :
why no Decepticons? 😜
2024-05-15 01:36:41
0
Plusacuss :
love your videos. you need such a larger following. anywhere not on tiktok to follow?
2024-05-15 00:08:36
1
parasoxical :
I learn something every time you speak
2024-05-14 23:46:37
1
iive.karry :
That’s interesting! Haven’t heard of it before
2024-05-14 23:10:31
1
FreePalestine :
💚👍
2025-02-10 21:54:08
0
smalltrak1 :
❤️❤️❤️
2025-01-20 21:43:47
0
irow :
Elon musk has no idea what he’s talking about 😭😭
2024-05-15 03:39:03
0
To see more videos from user @andrew_ships, please go to the Tikwm
homepage.