Paper Detail

OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

Donghyun Lee, Jitesh Chavan, Duy Nguyen, Sam Huang, Liming Jiang, Priyadarshini Panda, Timo Mertens, Saurabh Shukla

huggingface Score 4.5

Published 2026-07-02 · First seen 2026-07-06

General AI

Abstract

Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and guidance branches, forcing prior methods to re-fit calibration data for every new checkpoint or modality. We present OrbitQuant, a data-agnostic weight-activation quantizer that bypasses range estimation by quantizing in a normalized, rotated basis. In this basis, a randomized permuted block-Hadamard (RPBH) rotation concentrates each coordinate around one fixed, known marginal regardless of the input, so a single Lloyd-Max codebook serves all timesteps, prompts, and layers of a given input dimension. We extend the same quantizer to weight rows offline, absorbing the rotation into the weights so that it cancels inside each linear layer and only a forward rotation on the activations remains at runtime. The same recipe transfers from image to video with no per-modality tuning. Across FLUX.1, Z-Image-Turbo, Wan 2.1, and CogVideoX, it sets the state of the art for PTQ at several low-bit settings. It also pushes PTQ of image diffusion transformers to W2A4 with usable generation quality.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{lee2026orbitquant,
  title = {OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers},
  author = {Donghyun Lee and Jitesh Chavan and Duy Nguyen and Sam Huang and Liming Jiang and Priyadarshini Panda and Timo Mertens and Saurabh Shukla},
  year = {2026},
  abstract = {Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and guidance branches, forcing prior methods to re-fit calibration data for every new checkpoint or modality. We present OrbitQuant, a data-agnostic weight-activation quantizer that bypasses range estimation by quantizing in},
  url = {https://huggingface.co/papers/2607.02461},
  keywords = {diffusion transformers, post-training quantization, weight-activation quantizer, normalized rotated basis, randomized permuted block-Hadamard, Lloyd-Max codebook, quantization, diffusion models, image generation, video generation, huggingface daily},
  eprint = {2607.02461},
  archiveprefix = {arXiv},
}

Metadata

{}