Diffulab, a library to train diffusion models from scratch
Lately a friend of mine has been working on a personal project and I wanted to share it. The goal of Diffulab is to provide a flexible and modular framework for training diffusion models from scratch. The project is still in its early stages, and he is actively working on adding new features and improvements.
Diffulab, a library to train diffusion models from scratch launched on April 26, 2025 with 10 votes, #3,208 of 7,818 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
Diffulab is a library designed for training diffusion models from scratch. It provides a flexible and modular framework for machine learning researchers and developers working with generative AI. The project is currently in early development stages, with ongoing work to expand features and capabilities.
written from the facts on this page · September 2026
From the sources
DiffuLab is designed to provide a simple and flexible way to train diffusion models while allowing full customization of its core components. - LouisRouss/DiffuLab
git clone [email protected]:LouisRouss/DiffuLab.git cd DiffuLab uv sync uv pip install -e . Concept of the Library DiffuLab is designed to provide a simple and flexible way to train diffusion models while allowing full customization of its core components. The library is structured around three major building blocks: This project is in its early stages, and contributions are highly encouraged. The initial goal is to implement fundamental features and ensure they work seamlessly. Future updates will introduce additional functionalities, such as: To start training a model, follow the provided examples . Before running any training, make sure to configure accelerate in your terminal: accelerate…from github.com
Does a similar job
all alternatives →
Modular Diffusion – A modular Python library for diffusion models2023 · github.com · ▲40Hello everyone! I've been working on this project for a few months as part of my thesis in Machine Learning. It's meant to be a library that provides an easy-to-use but flexible API to design and train Diffusion Models. I decided to make it because I wanted to quickly prototype a Diffusion Model but there were no good tools to do it with. I think it really can help people prototype their own Diffusion Models a lot faster and only in a few lines of code. The base idea is to have a Model class that takes different modules corresponding to the different aspects of the Diffusion Model process…
Tiny Diffusion – A character-level text diffusion model from scratchNov 2025 · github.com · ▲172I previously posted this a month and a half ago: https://news.ycombinator.com/item?id=45876742 I have rewritten it to be much more simple, from 951 lines of code to just 364, with no loss in core functionality or generation quality. I also added a tiny GPT implementation as a comparison (inspired by Andrej Karpathy's code). The two model implementations are ~80% identical, with the core differences being the generate and get_batch functions. The model architecture, training loop, etc, differ in only 19 lines of code. Trained weights are included, so you can just clone and run…
- ILI left Figma to build a diffusion-based UI design toolJul 2026 · diffui.ai · ▲80
Hey hn, this has been something I've been working on for the last few months and is finally robust enough to really show off. I've been pretty tired with the design outputs of LLMs for a while, and I've always thought diffusion offered much more creative / on brand design outputs, even before they were able to render text. I had enough conviction for this to leave my role over at Figma to build Diffui. The goal is to allow for you to design your full web app as quickly as possible, in a figma-like interface, and then hand that off to an agent to build. The page shows some interactive…
- RLReadability-like API Using Machine Learning2011 · diffbot.com · ▲151
Documentation for Diffbot — transform the raw web into structured knowledge.
Steerling-8B, a language model that can explain any token it generatesFeb 2026 · guidelabs.ai · ▲328We release Steerling-8B, an 8B-parameter causal diffusion language model that is interpretable by construction — its predictions are routed through concepts you can measure, audit, and control.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, April 2025
the whole month →
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
The Unsure Calculator is an online tool that lets you calculate with numbers you’re not sure about.
Life & fun · 2025 · filiph.github.io
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
