# facebookresearch/DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Repository: https://github.com/facebookresearch/DiT
Canonical: https://ross.abutalabs.com/products/dit
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-05-31T13:04:15+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 96
- inputs: {"age_days": 1357, "days_push": 824, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8689, forks 810 (observed 2026-08-28T04:10:24.245734+00:00)

## What it is
Official PyTorch implementation of Diffusion Transformers (DiT) from the paper 'Scalable Diffusion Models with Transformers', including model definitions, pre-trained ImageNet weights, and training/sampling scripts. It replaces the U-Net backbone of latent diffusion models with a transformer operating on latent patches.

## Use cases
- generate class-conditional images with a diffusion transformer
- run pre-trained DiT-XL/2 models on ImageNet 256x256 or 512x512
- train a latent diffusion model with a transformer backbone instead of U-Net
- experiment with scalability of diffusion models measured in Gflops
- reproduce state-of-the-art FID results on class-conditional ImageNet generation

## When to choose
- you want the reference implementation of DiT with official pre-trained weights
- you need a simple, self-contained PyTorch codebase for diffusion transformer research
- you want to build on the architecture used by later models like Stable Diffusion 3

## When to avoid
- you need a production-ready text-to-image pipeline with broad feature support
- you want a maintained general-purpose diffusion library like Hugging Face diffusers
- you need models trained on datasets other than ImageNet class-conditional generation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, image-processing, artificial-intelligence
- platform: python
- tags: diffusion-models, transformers, pytorch, image-generation, research-code, pretrained-models, gpu, linux

## Member repositories
- facebookresearch/DiT (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:24.245734+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:25:34.957927+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/DiT (fetched 2026-08-28T04:10:24.245734+00:00, sha 7ae04750ef94)
- Data as of 2026-08-30T08:39:29.467469+00:00.