imagehub
Copyright 2026 imagehub contributors

The imagehub project is licensed under Apache License 2.0 except for files whose
headers and provenance records state another license. The PixelDiT implementation
in imagehub/models/pixeldit.py, imagehub/backends/pixeldit.py and corresponding
tests is a derivative of NVlabs PixelDiT and is licensed under NSCLv1 for
non-commercial research or evaluation only. Its upstream notice follows verbatim.

Implementation portions also derive from the projects identified in
THIRD_PARTY_NOTICES.md. Their copyright notices and license texts are retained in
licenses/. Pretrained checkpoints are not included and retain their publishers'
licenses when downloaded separately.

Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026
Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.

--------------------------------------------------------------------------------

PixelDiT / PixelDiT2
Copyright (c) NVIDIA Corporation

This repository is released under the license in LICENSE. It contains code
derived from the third-party projects listed below; their terms apply to the
corresponding files.

--------------------------------------------------------------------------------
PixNerd — https://github.com/MCG-NJU/PixNerd

  c2i/main.py
  c2i/src/data.py
  c2i/src/diffusion.py
  c2i/src/lightning.py
  c2i/src/utils.py
  pixdit_core/modules.py
  pixdit_core/pixeldit_c2i.py

--------------------------------------------------------------------------------
JiT — https://github.com/LTH14/JiT
MIT License, Copyright (c) 2025 Tianhong Li

  The PixelDiT2 backbone conventions (in-context class tokens, x-prediction with
  a velocity-space loss, the clipped velocity conversion) and the ODE samplers
  derive from this project.

  pixdit_core/pixeldit2_c2i.py
  c2i/src/grounded_diffusion.py

--------------------------------------------------------------------------------
guided-diffusion (ADM) — https://github.com/openai/guided-diffusion
MIT License, Copyright (c) 2021 OpenAI

  center_crop_arr in c2i/src/data.py.
  The FID protocol follows the ADM evaluation suite.

--------------------------------------------------------------------------------
REPA / REPA-E — https://github.com/sihyun-yu/REPA,
                https://github.com/End2End-Diffusion/REPA-E

  The representation alignment loss and the ImageNet preprocessing pipeline.

--------------------------------------------------------------------------------
SANA — https://github.com/NVlabs/SANA
Apache License 2.0

  The t2i/ subtree; per-file SPDX headers apply.

--------------------------------------------------------------------------------
Pretrained encoder weights

PixelDiT2 loads frozen vision encoders at runtime through `timm`; their weights
are not redistributed here and are governed by their own licenses.

  DINOv3 (grounding encoder) — Meta Platforms, DINOv3 License
    timm/vit_small_patch16_dinov3_qkvb.lvd1689m
    timm/vit_base_patch16_dinov3_qkvb.lvd1689m
    timm/vit_large_patch16_dinov3_qkvb.lvd1689m

  DINOv2 (REPA target, training only) — Meta Platforms, Apache License 2.0
    timm/vit_base_patch14_dinov2.lvd142m

The released PixelDiT2 checkpoints do not contain encoder weights. The frozen
encoder weights are loaded from timm at runtime.

--------------------------------------------------------------------------------
FID reference statistics

The ImageNet-256 and ImageNet-512 reference statistics used to reproduce the
reported FID values are the files tracked in the JiT repository
(https://github.com/LTH14/JiT, fid_stats/jit_in256_stats.npz and
fid_stats/jit_in512_stats.npz). They are not redistributed here.
