Pith Number

pith:4LMZRYZF

pith:2024:4LMZRYZFULW2QT7LIBJLYEBM3Q

not attested not anchored not stored refs resolved

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

Anran Wang, Shanchuan Lin, Xiao Yang

A distillation method combines progressive and adversarial training to enable one-step high-quality 1024-pixel image generation from SDXL.

arxiv:2402.13929 v3 · 2024-02-21 · cs.CV · cs.AI · cs.LG

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

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

We propose a diffusion distillation method that achieves new state-of-the-art in one-step/few-step 1024px text-to-image generation based on SDXL by combining progressive and adversarial distillation to achieve a balance between quality and mode coverage.

C2weakest assumption

The assumption that progressive adversarial training will maintain both perceptual quality and broad mode coverage without introducing artifacts or collapse, particularly when scaling the discriminator design and training schedule to the SDXL architecture.

C3one line summary

SDXL-Lightning uses progressive adversarial distillation to reach new state-of-the-art quality in one-step and few-step 1024px text-to-image generation from the SDXL base model.

References

82 extracted · 82 resolved · 1 Pith anchors

[1] https : / / civitai

[2] Stable video diffusion: Scaling latent video diffusion models to large datasets, 2023 2023

[3] Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, and Karsten Kreis 2023

[4] Coyo-700m: Image-text pair dataset 2022

[5] Pixart-$\alpha$: Fast training of diffusion transformer for photorealistic text-to-image syn- thesis 2024

Formal links

2 machine-checked theorem links

Cited by

18 papers in Pith

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting

Asymmetric Flow Models

ExpressEdit: Fast Editing of Stylized Facial Expressions with Diffusion Models in Photoshop

1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation

Receipt and verification

First computed	2026-05-17T23:38:15.037380Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e2d998e325a2eda84feb4052bc102cdc1c892ce6ec7d9a8b911010ba85775255

Aliases

arxiv: 2402.13929 · arxiv_version: 2402.13929v3 · doi: 10.48550/arxiv.2402.13929 · pith_short_12: 4LMZRYZFULW2 · pith_short_16: 4LMZRYZFULW2QT7L · pith_short_8: 4LMZRYZF

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/4LMZRYZFULW2QT7LIBJLYEBM3Q \
  | 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: e2d998e325a2eda84feb4052bc102cdc1c892ce6ec7d9a8b911010ba85775255

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "944b350b051a34f080e3d07ec97f5b20c4901bf62844bd2ddccf55539707df75",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2024-02-21T16:51:05Z",
    "title_canon_sha256": "81c5c4e9f2261c876842f43d5b9bd8f72c619adc558aa52d9377023389e7de38"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2402.13929",
    "kind": "arxiv",
    "version": 3
  }
}