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
• SwayStar123 / reimei
  ☆24Updated 5 months ago
• cloneofsimo / efae
  ☆23Updated last year
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆61Updated 7 months ago
• SwayStar123 / microdiffusion
  ☆49Updated 7 months ago
• ethansmith2000 / fsdp_optimizers
  supporting pytorch FSDP for optimizers
  ☆84Updated 9 months ago
• 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 6 months ago
• cloneofsimo / minDinoV2
  ☆21Updated 11 months ago
• cloneofsimo / zeroshampoo
  ☆34Updated last year
• fal-ai-community / llmdifftracker
  Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)
  ☆34Updated 7 months ago
• thinking-machines-lab / manifolds
  Supporting code for the blog post on modular manifolds.
  ☆39Updated last week
• cloneofsimo / min-max-in-dit
  ☆27Updated last year
• cloneofsimo / infinite-fractal-stream
  ☆30Updated 11 months ago
• fal-ai-community / alphabet-dataset
  Synthetic Alphabet Dataset
  ☆19Updated 6 months ago
• cloneofsimo / repa-rf
  ☆32Updated 11 months ago
• cloneofsimo / min-fsdp
  ☆89Updated last year
• bloc97 / DeMo
  DeMo: Decoupled Momentum Optimization
  ☆193Updated 10 months ago
• sayakpaul / nanoDiT
  Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
  ☆125Updated 4 months ago
• cloneofsimo / imagenet.int8
  ☆39Updated last year
• fal-ai-community / minDDPD
  ☆33Updated 8 months ago
• cloneofsimo / vqgan-training
  Train VAE like a boss
  ☆293Updated 11 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)
  ☆40Updated 7 months ago
• 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
• cloneofsimo / project_RF
  ☆24Updated last year
• apple / ml-ademamix
  ☆67Updated 10 months ago
• SonicCodes / lucid-v1
  realtime latent world model inference demo
  ☆47Updated 10 months ago
• surkovv / sdxl-unbox
  Sparse Autoencoders for Stable Diffusion XL models.
  ☆69Updated 2 months ago
• cloneofsimo / karras-power-ema-tutorial
  ☆53Updated last year
• idiap / sigma-gpt
  σ-GPT: A New Approach to Autoregressive Models
  ☆68Updated last year