Pith Number

pith:XFBNG3P6

pith:2021:XFBNG3P6ULQKUALPGAL6PJXPBZ

not attested not anchored not stored refs resolved

High-Resolution Image Synthesis with Latent Diffusion Models

Andreas Blattmann, Bj\"orn Ommer, Dominik Lorenz, Patrick Esser, Robin Rombach

Diffusion models trained in the latent space of pretrained autoencoders generate high-resolution images with substantially lower computational cost than pixel-space versions.

arxiv:2112.10752 v2 · 2021-12-20 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{XFBNG3P6ULQKUALPGAL6PJXPBZ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our latent diffusion models (LDMs) achieve a new state of the art for image inpainting and highly competitive performance on various tasks, including unconditional image generation, semantic scene synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

C2weakest assumption

That the latent representation produced by the pretrained autoencoder preserves enough perceptual detail and structure for the diffusion process to recover high-fidelity images without introducing artifacts that cannot be corrected by the model.

C3one line summary

Latent diffusion models achieve state-of-the-art inpainting and competitive results on unconditional generation, scene synthesis, and super-resolution by performing the diffusion process in the latent space of pretrained autoencoders with cross-attention conditioning, while cutting computational and

References

109 extracted · 109 resolved · 16 Pith anchors

[1] NTIRE 2017 chal- lenge on single image super-resolution: Dataset and study 2017

[2] Wasserstein gan 2017

[3] Large scale GAN training for high ﬁdelity natural image synthe- sis 2019

[4] Holger Caesar, Jasper R. R. Uijlings, and Vittorio Ferrari. Coco-stuff: Thing and stuff classes in context. In 2018 IEEE Conference on Computer Vision and Pattern Recog- nition, CVPR 2018, Salt Lake C 2018

[5] Extracting training data from large language models 2021

Cited by

138 papers in Pith

Stage-Aware Adaptation and Distribution Calibration for Subject-Driven Personalized Text-to-Image Generation

Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders

Tailor Made Embeddings for Quantum Machine Learning

SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing

UNITY: Attention Flow Networks for Adaptive Conditioning in Diffusion

Receipt and verification

First computed	2026-07-05T04:14:27.084189Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b942d36dfea2e0aa016f3017e7a6ef0e72610a251e77e9c777257a50a2a7e993

Aliases

arxiv: 2112.10752 · arxiv_version: 2112.10752v2 · doi: 10.48550/arxiv.2112.10752 · pith_short_12: XFBNG3P6ULQK · pith_short_16: XFBNG3P6ULQKUALP · pith_short_8: XFBNG3P6

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/XFBNG3P6ULQKUALPGAL6PJXPBZ \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: b942d36dfea2e0aa016f3017e7a6ef0e72610a251e77e9c777257a50a2a7e993

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bf3049144b7bde983b5d125b703794b3d857826a6753906bc996f3000aa600d6",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2021-12-20T18:55:25Z",
    "title_canon_sha256": "deec5d5eb94f2ddfe005fb1d91fc54db06e956ceabe8801103d39447982b0826"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2112.10752",
    "kind": "arxiv",
    "version": 2
  }
}