Pith Number

pith:W5HOEO55

pith:2024:W5HOEO55XSCA5OT2L5X5JMLG7D

not attested not anchored not stored refs resolved

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers

Enze Xie, Han Cai, Haotian Tang, Junsong Chen, Junyu Chen, Ligeng Zhu, Muyang Li, Song Han, Yao Lu, Yujun Lin, Zhekai Zhang

Sana-0.6B generates high-resolution images competitively with 12B-parameter models while running over 100 times faster on consumer GPUs.

arxiv:2410.10629 v3 · 2024-10-14 · 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{W5HOEO55XSCA5OT2L5X5JMLG7D}

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

Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput.

C2weakest assumption

The 32x deep-compression autoencoder preserves sufficient perceptual quality and text alignment at high resolutions without introducing artifacts that linear attention cannot correct.

C3one line summary

Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.

References

29 extracted · 29 resolved · 11 Pith anchors

[1] eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers · arXiv:2211.01324

[2] All are worth words: a vit backbone for score-based diffusion models 2022

[3] Language Models are Few-Shot Learners 2005 · arXiv:2005.14165

[4] Mahoney, and Kurt Keutzer 2020

[5] PixArt- : Weak-to-strong training of diffusion transformer for 4k text-to-image generation

Formal links

1 machine-checked theorem link

Cited by

36 papers in Pith

Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation

DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders

SURF: Signature-Retained Fast Video Generation

Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers

Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis

Receipt and verification

First computed	2026-05-17T23:39:05.189950Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b74ee23bbdbc840eba7a5f6fd4b166f8edfc5df31c739b840f04c5df7b535c9b

Aliases

arxiv: 2410.10629 · arxiv_version: 2410.10629v3 · doi: 10.48550/arxiv.2410.10629 · pith_short_12: W5HOEO55XSCA · pith_short_16: W5HOEO55XSCA5OT2 · pith_short_8: W5HOEO55

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/W5HOEO55XSCA5OT2L5X5JMLG7D \
  | 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: b74ee23bbdbc840eba7a5f6fd4b166f8edfc5df31c739b840f04c5df7b535c9b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "15afb39d277185e4366dd1119febf88c6db3f739196fb284b0c253610968d58f",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-10-14T15:36:42Z",
    "title_canon_sha256": "e95928638dc8b30e52d7551e409e10ea8ac631fff31b5419ab2807f3683bd070"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2410.10629",
    "kind": "arxiv",
    "version": 3
  }
}