Pith Number

pith:4ZVQJD6U

pith:2023:4ZVQJD6UAPPG6ELL3QINWN4WWF

not attested not anchored not stored refs resolved

TokenFlow: Consistent Diffusion Features for Consistent Video Editing

Michal Geyer, Omer Bar-Tal, Shai Bagon, Tali Dekel

Enforcing consistency among diffusion features across frames yields temporally coherent text-driven video edits.

arxiv:2307.10373 v3 · 2023-07-19 · 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{4ZVQJD6UAPPG6ELL3QINWN4WWF}

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

consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space... by explicitly propagating diffusion features based on inter-frame correspondences

C2weakest assumption

That propagating diffusion features according to inter-frame correspondences will produce spatially and temporally consistent edits without introducing new artifacts or breaking the text conditioning.

C3one line summary

TokenFlow produces consistent text-driven video edits by propagating diffusion features according to inter-frame correspondences extracted from the source video.

References

27 extracted · 27 resolved · 7 Pith anchors

[1] Multidiffusion: Fusing diffusion paths for controlled image generation

[2] Pix2video: Video editing using image diffusion

[3] Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models

[4] Diffusion models in vision: A survey.arXiv e-prints, abs/2209.04747

[5] Structure and content-guided video synthesis with diffusion models

Cited by

26 papers in Pith

We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback

TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training

Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioning

VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers

LatentUMM: Dual Latent Alignment for Unified Multimodal Models

Receipt and verification

First computed	2026-05-17T23:38:13.200350Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62

Aliases

arxiv: 2307.10373 · arxiv_version: 2307.10373v3 · doi: 10.48550/arxiv.2307.10373 · pith_short_12: 4ZVQJD6UAPPG · pith_short_16: 4ZVQJD6UAPPG6ELL · pith_short_8: 4ZVQJD6U

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/4ZVQJD6UAPPG6ELL3QINWN4WWF \
  | 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: e66b048fd403de6f116bdc10db3796b1491fca2c929748c729c6372b9fe48c62

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b96ec8c6351673bf7ed8019ebd9f1eb0f2ee97edac7e2bd78e5884173c3ed0cf",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-07-19T18:00:03Z",
    "title_canon_sha256": "dbea7345e122a1e97e220cee9e14684f92d07d9632b7f26ed75e64ce59eb04e7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2307.10373",
    "kind": "arxiv",
    "version": 3
  }
}