pith:TTWPTCLF
Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation
An adapted Kaplan scaling law predicts GPU energy use for diffusion models from FLOPs.
arxiv:2511.17031 v2 · 2025-11-21 · cs.LG · cs.CV · cs.CY
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{TTWPTCLF73VTHWTHTU7DKTBP72}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Our energy scaling law achieves high predictive accuracy within individual architectures (R² > 0.9) and exhibits strong cross-architecture generalization, maintaining high rank correlations across models and enabling reliable energy estimation for unseen model–hardware combinations.
denoising operations dominate energy consumption due to their repeated execution across multiple inference steps
An adapted scaling law predicts GPU energy consumption for diffusion model inference with R² > 0.9 within architectures and strong cross-architecture generalization.
References
Formal links
Receipt and verification
| First computed | 2026-05-18T03:10:11.796250Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
9cecf98965feeb33da679d3e354c2ffe82dcd5e5e297158998c01681294b0200
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/TTWPTCLF73VTHWTHTU7DKTBP72 \
| 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: 9cecf98965feeb33da679d3e354c2ffe82dcd5e5e297158998c01681294b0200
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "005f4259b6fe21a22155a1478a2114325e997777214ca29617d05d8e5a8e6fad",
"cross_cats_sorted": [
"cs.CV",
"cs.CY"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2025-11-21T08:12:47Z",
"title_canon_sha256": "27cd6c96af1f6e27af6aacab836b4eb0447ee92fc058e070a7a2efd42f56eed7"
},
"schema_version": "1.0",
"source": {
"id": "2511.17031",
"kind": "arxiv",
"version": 2
}
}