andylolu2 / jax-diffusion
Implementation of Denoising Diffusion Probabilistic Models (DDPM) in JAX and Flax.
☆20Updated last year
Alternatives and similar repositories for jax-diffusion:
Users that are interested in jax-diffusion are comparing it to the libraries listed below
- FID computation in Jax/Flax.☆27Updated 9 months ago
- Flow-matching algorithms in JAX☆89Updated 8 months ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆56Updated last month
- ☆30Updated 5 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆24Updated 3 months ago
- Official Jax Implementation of MD4 Masked Diffusion Models☆77Updated last month
- Lightning-like training API for JAX with Flax☆38Updated 4 months ago
- Implementation of PSGD optimizer in JAX☆31Updated 3 months ago
- Unofficial implementation of GotenNet, new SOTA 3d equivariant transformer, in Pytorch☆59Updated 2 weeks ago
- This is a port of Mistral-7B model in JAX☆32Updated 9 months ago
- Pytorch implementation of a simple way to enable (Stochastic) Frame Averaging for any network☆49Updated 9 months ago
- ICML 2022: Learning Iterative Reasoning through Energy Minimization☆46Updated 2 years ago
- Pytorch-like dataloaders for JAX.☆80Updated this week
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆83Updated last year
- ☆31Updated last year
- Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems☆45Updated last week
- ☆33Updated 7 months ago
- ☆28Updated 3 weeks ago
- ☆63Updated 10 months ago
- Code release for "Stochastic Optimal Control Matching"☆33Updated 8 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆30Updated this week
- The Gaussian Histogram Loss (HL-Gauss) proposed by Imani et al. with a few convenient wrappers for regression, in Pytorch☆58Updated 2 months ago
- ☆34Updated 3 months ago
- Implementation of papers in 101 lines of code.☆18Updated last year
- Explorations into whether a transformer with RL can direct a genetic algorithm to converge faster☆67Updated this week
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated last year
- JAX Implementation of Black Forest Labs' Flux.1 family of models☆31Updated 6 months ago
- ☆102Updated this week
- Turn jitted jax functions back into python source code☆22Updated 4 months ago
- Improved sampling via learned diffusions (ICLR2024) and an optimal control perspective on diffusion-based generative modeling (TMLR2024)☆61Updated last month