Pinned Repositories
fast-DiT
Fast Diffusion Models with Transformers
diffusion-feature
Use pretrained Stable Diffusion model to extract features for various vision tasks
ViewDiff
ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).
ddae
[ICCV 2023 Oral] Official Implementation of "Denoising Diffusion Autoencoders are Unified Self-supervised Learners"
InfoBatch
Lossless Training Speed Up by Unbiased Dynamic Data Pruning
DiffMemorize
On Memorization in Diffusion Models
MDT
Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)
Erasing-Adversarial-Preservation
NeurIPS 2024 - Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
Data-Selection-and-Reweighting-for-Diffusion-Models
Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
DFTND
Yeez-lee's Repositories
Yeez-lee/Data-Selection-and-Reweighting-for-Diffusion-Models
Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
Yeez-lee/DFTND