Alternatives and similar repositories for TokenBench:

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

• LargeWorldModel / ElasticTok
  ElasticTok: Adaptive Tokenization for Image and Video
  ☆67Updated 6 months ago
• phyworld / phyworld
  ☆126Updated 4 months ago
• yifan123 / flow_grpo
  An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
  ☆170Updated this week
• wilson1yan / teco
  ☆116Updated 2 months ago
• causalfusion / causalfusion
  ☆159Updated 4 months ago
• yinboc / dito
  Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"
  ☆113Updated 3 months ago
• microsoft / Reducio-VAE
  ☆193Updated 2 months ago
• kwsong0113 / diffusion-forcing-transformer
  Official PyTorch Implementation of "History-Guided Video Diffusion"
  ☆306Updated 2 months ago
• ShivamDuggal4 / adaptive-length-tokenizer
  Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?
  ☆118Updated 3 months ago
• facebookresearch / metamorph
  Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning
  ☆156Updated 3 weeks ago
• huiwon-jang / CoordTok
  ☆30Updated 3 months ago
• NVlabs / QLIP
  [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
  ☆70Updated 2 months ago
• YuqingWang1029 / PAR
  [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project
  ☆151Updated last month
• facebookresearch / EvalGIM
  🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…
  ☆74Updated 4 months ago
• Hritikbansal / videophy
  Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics
  ☆93Updated this week
• Video-as-Agent / VideoAgent
  Official implementation of "Self-Improving Video Generation"
  ☆66Updated 2 weeks ago
• hywang66 / LARP
  Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).
  ☆68Updated 2 months ago
• TIGER-AI-Lab / VideoScore
  official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]
  ☆88Updated 2 months ago
• jsu27 / decomp_diffusion
  [ICML 2024] Compositional Image Decomposition with Diffusion Models
  ☆50Updated 10 months ago
• songweige / content-debiased-fvd
  [CVPR 2024] On the Content Bias in Fréchet Video Distance
  ☆111Updated 7 months ago
• NJU-PCALab / OpenVid-1M
  [ICLR 2025] OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
  ☆289Updated 2 months ago
• MonoFormer / MonoFormer
  The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"
  ☆86Updated 6 months ago
• SilentView / GigaTok
  Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"
  ☆142Updated 2 weeks ago
• Gengzigang / TokenSet
  Official PyTorch implementation of TokenSet.
  ☆118Updated last month
• baaivision / MUSE-Pytorch
  An in-context conditioning version of MUSE with pre-trained checkpoints.
  ☆111Updated last year
• End2End-Diffusion / REPA-E
  Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers
  ☆190Updated 3 weeks ago
• NVlabs / T-Stitch
  [ICLR 2025] Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stit…
  ☆101Updated last year
• THUDM / VisionReward
  VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
  ☆235Updated last month
• alexanderswerdlow / unidisc
  UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…
  ☆94Updated last month
• vision-x-nyu / pisa-experiments
  Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)
  ☆29Updated this week