Alternatives and similar repositories for decomp_diffusion

Users that are interested in decomp_diffusion are comparing it to the libraries listed below

• yuanzhi-zhu / SlimFlow
  "SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow", Yuanzhi Zhu, Xingchao Liu, Qiang Liu
  ☆51Updated 6 months ago
• ShivamDuggal4 / adaptive-length-tokenizer
  Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?
  ☆122Updated 4 months ago
• yinboc / dito
  Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"
  ☆125Updated 4 months ago
• LargeWorldModel / ElasticTok
  ElasticTok: Adaptive Tokenization for Image and Video
  ☆70Updated 7 months ago
• nanlliu / Unsupervised-Compositional-Concepts-Discovery
  [ICCV 2023] Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models
  ☆84Updated last year
• shim0114 / SSM-Meets-Video-Diffusion-Models
  ☆48Updated 3 months ago
• Hritikbansal / videophy
  Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics
  ☆119Updated last month
• yangxiaofeng / rectified_flow_prior
  Official code for paper: Text-to-Image Rectified Flow as Plug-and-Play Priors [ICLR 2025]
  ☆124Updated 2 months ago
• KAIST-Visual-AI-Group / Flow-Inference-Time-Scaling
  Official code for Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing
  ☆57Updated 3 weeks ago
• Wuziyi616 / SlotDiffusion
  Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models
  ☆88Updated last year
• slowfast-vgen / slowfast-vgen
  ☆21Updated 7 months ago
• visual-gen / semanticist
  Code for paper "Principal Components" Enable A New Language of Images
  ☆44Updated 2 weeks ago
• salesforce / DOODL
  ☆68Updated 4 months ago
• sangyun884 / rfpp
  The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024
  ☆114Updated 8 months ago
• tzco / Diffusion-wo-CFG
  Official Implementation for Diffusion Models Without Classifier-free Guidance
  ☆130Updated 4 months ago
• xiefan-guo / initno
  [CVPR 2024] InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
  ☆63Updated last year
• NVlabs / QLIP
  [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
  ☆75Updated 3 months ago
• a1600012888 / LaCT
  Code release for paper "Test-Time Training Done Right"
  ☆149Updated this week
• LabForComputationalVision / memorization_generalization_in_diffusion_models
  ☆46Updated last year
• NVlabs / DDO
  [ICML 2025 Spotlight] Direct Discriminative Optimization: Supercharging Diffusion/Autoregressive with GAN-type Discrimination
  ☆47Updated this week
• JindongJiang / latent-slot-diffusion
  Official Release of NeurIPS 2023 Spotlight paper "Object-Centric Slot Diffusion"
  ☆66Updated last year
• FutureXiang / edm2
  Minimal multi-gpu implementation of EDM2: "Analyzing and Improving the Training Dynamics of Diffusion Models"
  ☆32Updated last year
• diffusion-hyperfeatures / diffusion_hyperfeatures
  Official PyTorch Implementation for Diffusion Hyperfeatures, NeurIPS 2023
  ☆103Updated 8 months ago
• geonyeong-park / Spectral-Motion-Alignment
  The official repository of "Spectral Motion Alignment for Video Motion Transfer using Diffusion Models".
  ☆27Updated 6 months ago
• thu-ml / CCA
  Codes accompanying the paper "Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment"
  ☆33Updated 4 months ago
• lzzcd001 / nabla-gfn
  Official Implementation of Nabla-GFlowNet (ICLR 2025)
  ☆20Updated last month
• huiwon-jang / CoordTok
  ☆36Updated 4 months ago
• oooolga / Ctrl-V
  👆Pytorch implementation of "Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion"
  ☆27Updated 8 months ago
• xizaoqu / MOFT
  [Neurips 2024] Video Diffusion Models are Training-free Motion Interpreter and Controller
  ☆41Updated 2 months ago
• lukaslaobeyer / token-opt
  Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"
  ☆80Updated 2 weeks ago