Alternatives and similar repositories for diffusion-speedrun

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

• SwayStar123 / reimei
  ☆28Updated 3 months ago
• cloneofsimo / scaling-guide
  WIP
  ☆93Updated last year
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆63Updated 10 months ago
• cloneofsimo / min-max-gpt
  Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training
  ☆132Updated last year
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated last year
• cloneofsimo / efae
  ☆23Updated last year
• SwayStar123 / microdiffusion
  ☆48Updated 10 months ago
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆198Updated last year
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• fal-ai-community / llmdifftracker
  Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)
  ☆34Updated 10 months ago
• cloneofsimo / min-max-in-dit
  ☆27Updated last year
• cloneofsimo / minDinoV2
  ☆23Updated last year
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆56Updated 10 months ago
• cloneofsimo / imagenet.int8
  ☆39Updated last year
• cloneofsimo / infinite-fractal-stream
  ☆30Updated last year
• fal-ai-community / alphabet-dataset
  Synthetic Alphabet Dataset
  ☆19Updated 9 months ago
• cloneofsimo / vqgan-training
  Train VAE like a boss
  ☆311Updated last year
• cloneofsimo / min-fsdp
  ☆92Updated 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
  ☆85Updated last year
• fal-ai-community / minDDPD
  ☆33Updated last year
• apple / ml-ademamix
  ☆70Updated last year
• sayakpaul / nanoDiT
  Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
  ☆142Updated 7 months ago
• 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 10 months ago
• cloneofsimo / repa-rf
  ☆32Updated last year
• bluorion-com / ZClip
  Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".
  ☆141Updated last month
• cloneofsimo / project_RF
  ☆24Updated last year
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆111Updated 3 months ago
• lucidrains / hyper-connections
  Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public
  ☆139Updated this week
• cloneofsimo / karras-power-ema-tutorial
  ☆53Updated 2 years ago
• lucidrains / maskbit-pytorch
  Implementation of the proposed MaskBit from Bytedance AI
  ☆83Updated last year