Alternatives and similar repositories for diffusion-speedrun

Users that are interested in diffusion-speedrun are comparing it to the libraries listed below

• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• cloneofsimo / efae
  ☆23Updated last year
• SwayStar123 / microdiffusion
  ☆48Updated 10 months ago
• SwayStar123 / reimei
  ☆28Updated 2 months ago
• cloneofsimo / vqgan-training
  Train VAE like a boss
  ☆309Updated last year
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated last year
• cloneofsimo / min-max-in-dit
  ☆27Updated last year
• cloneofsimo / minDinoV2
  ☆22Updated last year
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆56Updated 9 months ago
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆63Updated 10 months ago
• cloneofsimo / imagenet.int8
  ☆39Updated last year
• fal-ai-community / minDDPD
  ☆33Updated 11 months ago
• cloneofsimo / min-fsdp
  ☆91Updated last year
• cloneofsimo / repa-rf
  ☆32Updated last year
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆197Updated last year
• fal-ai-community / alphabet-dataset
  Synthetic Alphabet Dataset
  ☆19Updated 8 months ago
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• lucidrains / spline-based-transformer
  Implementation of the proposed Spline-Based Transformer from Disney Research
  ☆105Updated last year
• sayakpaul / nanoDiT
  Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
  ☆141Updated 6 months ago
• cloneofsimo / infinite-fractal-stream
  ☆30Updated last year
• cloneofsimo / project_RF
  ☆24Updated last year
• cloneofsimo / ezmup
  Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
  ☆84Updated last year
• apple / ml-ademamix
  ☆69Updated last year
• stanislavfort / Direct_Ascent_Synthesis
  A demo for the Direct Ascent Synthesis: Hidden Generative Capabilities in Discriminative Models paper (https://arxiv.org/abs/2502.07753)
  ☆41Updated 9 months ago
• fal-ai-community / llmdifftracker
  Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)
  ☆34Updated 9 months ago
• lucidrains / maskbit-pytorch
  Implementation of the proposed MaskBit from Bytedance AI
  ☆83Updated last year
• bluorion-com / ZClip
  Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".
  ☆141Updated last month
• crowsonkb / consistency-models
  A JAX implementation of the continuous time formulation of Consistency Models
  ☆85Updated 2 years ago
• SerChirag / rs-imle
  RS-IMLE
  ☆43Updated last year