Alternatives and similar repositories for capi

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

• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• google-deepmind / tips
  TIPS (ICLR'25): Text-Image Pretraining with Spatial Awareness
  ☆110Updated 8 months ago
• philippe-eecs / vitok
  ☆34Updated 7 months ago
• lucidrains / titok-pytorch
  Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"
  ☆183Updated last year
• cloneofsimo / vqgan-training
  Train VAE like a boss
  ☆309Updated last year
• KellerJordan / cifar10-airbench
  CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
  ☆336Updated last month
• apple / ml-sigmoid-attention
  ☆303Updated 8 months ago
• facebookresearch / webssl
  Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).
  ☆192Updated 7 months ago
• apple / ml-flextok
  FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
  ☆279Updated 6 months ago
• fal-ai-community / alphabet-dataset
  Synthetic Alphabet Dataset
  ☆19Updated 9 months ago
• goombalab / hydra
  Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"
  ☆167Updated 10 months ago
• facebookresearch / Mixture-of-Transformers
  Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.
  ☆132Updated 3 months ago
• facebookresearch / EvalGIM
  🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…
  ☆90Updated last year
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆76Updated last year
• nickjiang2378 / test-time-registers
  [NeurIPS '25 Spotlight] Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"
  ☆156Updated 3 months ago
• martin-marek / batch-size
  📄Small Batch Size Training for Language Models
  ☆69Updated 2 months ago
• dome272 / Flow-Matching
  My take on Flow Matching
  ☆86Updated 11 months ago
• rbalestr-lab / lejepa
  ☆770Updated 2 weeks ago
• lucidrains / multimodal-dit-pytorch
  Implementation of a multimodal diffusion transformer in Pytorch
  ☆107Updated last year
• ChenWu98 / algorithmic-creativity
  [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
  ☆82Updated 7 months ago
• cloneofsimo / karras-power-ema-tutorial
  ☆53Updated last year
• ShivamDuggal4 / adaptive-length-tokenizer
  Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?
  ☆141Updated 10 months ago
• cloneofsimo / minDinoV2
  ☆22Updated last year
• riverstone496 / awesome-second-order-optimization
  ☆27Updated 2 months ago
• cloneofsimo / min-fsdp
  ☆91Updated last year
• lucidrains / nGPT-pytorch
  Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI
  ☆294Updated 6 months ago
• helblazer811 / ConceptAttention
  ConceptAttention: A method for interpreting multi-modal diffusion transformers.
  ☆400Updated last month
• gregorbachmann / scaling_mlps
  ☆52Updated last year
• Kai-46 / minFM
  ☆167Updated 2 months ago
• lukaslaobeyer / token-opt
  Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"
  ☆195Updated 6 months ago