zdxiao / DDPM_vs_FlowMatchingLinks
Diffusion Model Experiment: Fitting an Elliptical Distribution, Flow Matching Proves More Efficient than DDPM The experiment compares training efficiency and sampling trajectories between DDPM (trained with DDPM and sampled with DDIM) and Flow Matching. It highlights the differences in performance during the model training process.
☆37Updated last year
Alternatives and similar repositories for DDPM_vs_FlowMatching
Users that are interested in DDPM_vs_FlowMatching are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models☆319Updated 9 months ago
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"☆426Updated 7 months ago
- A collection of diffusion models based on FLUX/DiT for image/video generation, editing, reconstruction, inpainting .etc.☆85Updated 7 months ago
- [ICLR2025] The code of Z-Sampling, proposed in our paper "Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflectio…☆99Updated 11 months ago
- [NeurIPS 2025 D&B🔥] ImgEdit: A Unified Image Editing Dataset and Benchmark☆276Updated 3 months ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆206Updated 6 months ago
- CAR: Controllable AutoRegressive Modeling for Visual Generation☆128Updated last year
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆451Updated 2 months ago
- [CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention☆178Updated 11 months ago
- 【CVPR 2025 Oral】Official Repo for Paper "AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea"☆214Updated 10 months ago
- [CVPR 2025🔥] Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model☆194Updated 9 months ago
- [NeurIPS 2024] Official implementation of "BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models…☆140Updated 8 months ago
- Frequency Autoregressive Image Generation with Continuous Tokens☆94Updated 8 months ago
- Implements VAR+CLIP for text-to-image (T2I) generation☆147Updated last year
- [ICCV 2025] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE☆386Updated last year
- [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process☆626Updated this week
- [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think☆244Updated 4 months ago
- Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"☆292Updated 9 months ago
- [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".☆195Updated 6 months ago
- 🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook☆105Updated last year
- This is a repository to collect training-free algorithms for visual generation and manipulation☆209Updated last week
- Official code for K-LoRA (CVPR 2025)☆140Updated 4 months ago
- An official implementation of Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching☆64Updated 5 months ago
- Official PyTorch implementation of DiffMoE, TC-DiT, EC-DiT and Dense DiT☆163Updated 3 months ago
- ☆176Updated 7 months ago
- Towards Scalable Pre-training of Visual Tokenizers for Generation☆440Updated last month
- ☆80Updated last year
- [ICLR 2026] The official implementation of "RegionE: Adaptive Region-Aware Generation for Efficient Image Editing"☆76Updated last week
- [CVPR 2025] Attention Distillation: A Unified Approach to Visual Characteristics Transfer☆226Updated 11 months ago
- [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Mo…☆329Updated 8 months ago