Frank Fundel
@frankfundel.bsky.social
📤 17
📥 8
📝 11
PhD Student @ LMU Munich
https://ffundel.de/
pinned post!
Did you know you can distill the capabilities of a large diffusion model into a small ViT? ⚗️ We showed exactly that for a fundamental task: semantic correspondence📍 A thread 🧵👇
11 months ago
1
4
4
reposted by
Frank Fundel
CompVis - Computer Vision and Learning LMU Munich
5 months ago
🧹 CleanDiFT: Diffusion Features without Noise
@rmsnorm.bsky.social
*,
@stefanabaumann.bsky.social
*,
@koljabauer.bsky.social
*,
@frankfundel.bsky.social
, Björn Ommer Oral Session 1C (Davidson Ballroom): Friday 9:00 Poster Session 1 (ExHall D): Friday 10:30-12:30, # 218
compvis.github.io/cleandift/
loading . . .
CleanDIFT: Diffusion Features without Noise
CleanDIFT enables extracting Noise-Free, Timestep-Independent Diffusion Features
https://compvis.github.io/cleandift/
1
8
3
Did you know you can distill the capabilities of a large diffusion model into a small ViT? ⚗️ We showed exactly that for a fundamental task: semantic correspondence📍 A thread 🧵👇
11 months ago
1
4
4
you reached the end!!
feeds!
log in
