Pith Number

pith:IFFFKKEE

pith:2022:IFFFKKEEWO523YN76RUL6YEBP4

not attested not anchored not stored refs resolved

DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models

Cheng Lu, Chongxuan Li, Fan Bao, Jianfei Chen, Jun Zhu, Yuhao Zhou

DPM-Solver++ generates high-quality guided samples from diffusion models in 15 to 20 steps

arxiv:2211.01095 v3 · 2022-11-02 · cs.LG · 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{IFFFKKEEWO523YN76RUL6YEBP4}

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

Experiments show that DPM-Solver++ can generate high-quality samples within only 15 to 20 steps for guided sampling by pixel-space and latent-space DPMs.

C2weakest assumption

That the combination of data-prediction formulation and thresholding, plus the multistep variant, reliably eliminates the instability observed in prior high-order solvers when guidance scale is large.

C3one line summary

DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.

References

30 extracted · 30 resolved · 4 Pith anchors

[1] Estimating the optimal covariance with imperfect mean in diffusion probabilistic models

[2] Classifier-free diffusion guidance 2021

[3] Gotta go fast when generating data with score-based models

[4] On fast sampling of diffusion probabilistic models

[5] Bilateral denoising diffusion models

Formal links

2 machine-checked theorem links

Cited by

40 papers in Pith

DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows

Improved DDIM Sampling with Moment Matching Gaussian Mixtures

SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation

UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models

Sampling-Aware Quantization for Diffusion Models

Receipt and verification

First computed	2026-05-17T23:38:48.596639Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

414a552884b3bbade1bff468bf60817f3272773873f6e20d4c138d9d99a1c31f

Aliases

arxiv: 2211.01095 · arxiv_version: 2211.01095v3 · doi: 10.48550/arxiv.2211.01095 · pith_short_12: IFFFKKEEWO52 · pith_short_16: IFFFKKEEWO523YN7 · pith_short_8: IFFFKKEE

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/IFFFKKEEWO523YN76RUL6YEBP4 \
  | 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: 414a552884b3bbade1bff468bf60817f3272773873f6e20d4c138d9d99a1c31f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2988b52dbb2d98e7850193f87431af48282a2efbb47e95cbc5a69c7fe45895b2",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2022-11-02T13:14:30Z",
    "title_canon_sha256": "6fb94dc7b65c3a0888ddd207f6d8d4a4dc92e723d10cf97e60d056e20af0f2f3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2211.01095",
    "kind": "arxiv",
    "version": 3
  }
}