Diffusion model - Wikipedia
5
公开标注数
5
参与人数
2026-07-15 10:01:48
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-15 13:22:48
原文高亮摘录
“Diffusion-based image generators have seen widespread commercial interest, such as Stable Diffusion and DALL-E”
Whisper 随想笔记
I still can't tell if these are actually good or just hype
划选高亮2026-07-15 13:13:48
原文高亮摘录
“Diffusion-based image generators have seen widespread commercial interest, such as Stable Diffusion and DALL-E”
Whisper 随想笔记
Yeah but everyone's just making weird memes with them honestly
划选高亮2026-07-15 10:19:48
原文高亮摘录
“diffusion models, also known as diffusion-based generative models or score-based generative models, are a class of latent variable generative models”
Whisper 随想笔记
Makes sense if you think of it as reverse-engineering noise to get data back.
划选高亮2026-07-15 10:10:48
原文高亮摘录
“diffusion models, also known as diffusion-based generative models or score-based generative models, are a class of latent variable generative models”
Whisper 随想笔记
I've seen these called score-based too, but the latent variable framing still throws me off.
划选高亮2026-07-15 10:01:48
原文高亮摘录
“diffusion models, also known as diffusion-based generative models or score-based generative models, are a class of latent variable generative models”
Whisper 随想笔记
So it's basically a fancy random walk that learns how to un-blur images?
分享本页 Whisper
短链接
https://domwhisper.com/s/4347112ea953嵌入代码
<iframe src="https://domwhisper.com/embed/4347112ea953" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>