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.
☆32Updated 7 months ago
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:
- Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"☆402Updated 2 months ago
- [ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models☆286Updated 4 months ago
- [NeurIPS 2024] Official implementation of "BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models…☆133Updated 3 months ago
- CAR: Controllable AutoRegressive Modeling for Visual Generation☆123Updated 9 months ago
- [ICLR2025] The code of Z-Sampling, proposed in our paper "Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflectio…☆83Updated 6 months ago
- Implements VAR+CLIP for text-to-image (T2I) generation☆148Updated 7 months ago
- A collection of diffusion models based on FLUX/DiT for image/video generation, editing, reconstruction, inpainting .etc.☆84Updated 2 months ago
- ☆76Updated 8 months ago
- [ICCV 2025] VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE☆353Updated 7 months ago
- Official implementation of the paper "Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirect…☆188Updated 4 months ago
- [CVPR 2025] Attention Distillation: A Unified Approach to Visual Characteristics Transfer☆201Updated 6 months ago
- 【CVPR 2025 Oral】Official Repo for Paper "AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea"☆184Updated 5 months ago
- [ICLR 2025] Autoregressive Video Generation without Vector Quantization☆567Updated last week
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆194Updated 2 months ago
- This is a repo to track the latest autoregressive visual generation papers.☆394Updated 2 months ago
- ☆197Updated last year
- [ICLR2024] The official implementation of paper "VDT: General-purpose Video Diffusion Transformers via Mask Modeling", by Haoyu Lu, Guoxi…☆242Updated last year
- 🔥stable, simple, state-of-the-art VQVAE toolkit & cookbook☆100Updated last year
- [NeurIPS 2024] The official code of "U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers"☆217Updated 11 months ago
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆422Updated 10 months ago
- [TMLR 2025🔥] A survey for the autoregressive models in vision.☆693Updated last week
- [ICCV 2025][Few-Step Student Surpasses Teacher Diffusion] Learning Few-Step Diffusion Models by Trajectory Distribution Matching☆50Updated last month
- Frequency Autoregressive Image Generation with Continuous Tokens☆86Updated 3 months ago
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆339Updated 2 months ago
- Official code for K-LoRA (CVPR 2025)☆122Updated 3 months ago
- OneIG-Bench is a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models across multiple dimens…☆67Updated last month
- Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"☆257Updated 4 months ago
- Improving Video Generation with Human Feedback☆291Updated last month
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆167Updated last week
- This is a repository to collect training-free algorithms for visual generation and manipulation☆114Updated last week