CompVis / distilldift
DistillDIFT: Distillation of Diffusion Features for Semantic Correspondence (WACV 2025)
☆18Updated last month
Alternatives and similar repositories for distilldift:
Users that are interested in distilldift are comparing it to the libraries listed below
- ☆42Updated this week
- Personalized Representation from Personalized Generation (ICLR 2025)☆51Updated this week
- This is a PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Framework for Cross-Modality Evolu…☆134Updated last week
- Unsupervised Semantic Correspondence Using Stable Diffusion☆56Updated last year
- ☆68Updated 3 months ago
- Official PyTorch Implementation for Diffusion Hyperfeatures, NeurIPS 2023☆99Updated 4 months ago
- [ECCV 2024] DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control☆69Updated 3 months ago
- ☆88Updated last month
- Official code for "DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut", NeurIPS 202…☆37Updated last month
- ☆45Updated 8 months ago
- [NeurIPS 24] Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models☆36Updated 5 months ago
- Towards training VQ-VAE models robustly!☆54Updated last month
- [CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention☆124Updated this week
- This is the official implementation for ControlVAR.☆95Updated 2 months ago
- The official implementation of "[MASK] is All You Need"☆111Updated this week
- Code for "Don’t drop your samples! Coherence-aware training benefits Conditional diffusion" CVPR 2024 Highlight☆50Updated last month
- High order Moment Models☆37Updated this week
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆97Updated 4 months ago
- ☆43Updated 6 months ago
- [CVPR 2025] Open implementation of "RandAR"☆57Updated last month
- ☆14Updated this week
- Diffusion Models as Data Mining Tools☆53Updated 4 months ago
- ☆141Updated 2 months ago
- Official code for paper: Text-to-Image Rectified Flow as Plug-and-Play Priors [ICLR 2025]☆103Updated 2 weeks ago
- ☆25Updated 2 months ago