Introduction
Lumiere uses a space–time U-Net that processes the full video duration in a model pass, offering an alternative to sparse keyframes followed by temporal interpolation.
View full image ↗Figure 1: stills from Lumiere generation and inpainting tasks; the project videos are needed to see motion. Source: v2; the image version is distinct from the initial submission date.
Bar-Tal, Omer; Chefer, Hila; Tov, Omer; Herrmann, Charles; Paiss, Roni; Zada, Shiran; Ephrat, Ariel; Hur, Junhwa; Liu, Guanghui; Raj, Amit; Li, Yuanzhen; Rubinstein, Michael; Michaeli, Tomer; Wang, Oliver; Sun, Deqing; Dekel, Tali; Mosseri, Inbar · original paper / arXiv · Rights in the paper and depicted works remain with their holders. Research quotation does not establish an open licence; republication rights await independent review.
Source · Lumiere: A Space-Time Diffusion Model for Video Generation ↗RESEARCH ACCOUNT
Lumiere uses a space–time U-Net that processes the full video duration in a model pass, offering an alternative to sparse keyframes followed by temporal interpolation.
ANTI-AI ARCHIVE · Revised 2026-10-03
What the paper investigates
Spatial and temporal downsampling and upsampling let the network process a full-duration, low-resolution clip at multiple scales, using a pretrained image model. Demonstrations include text-to-video, image-to-video, video inpainting and stylised generation.
Section sources: Lumiere: A Space-Time Diffusion Model for Video Generation
Its place in generative-art history
Editorial interpretation: temporal coherence can be an architectural issue rather than only a post-generation repair. The entry supports comparison of how a shot is organised, beyond ranking services by image quality or release date.
Section sources: Lumiere: A Space-Time Diffusion Model for Video Generation
Reading limits and versions
Processing the full duration in one forward pass does not mean one denoising step; generation still uses a diffusion process.
Section sources: Lumiere: A Space-Time Diffusion Model for Video Generation
Sources for this account
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited.
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Lumiere: compare methods, control or evaluation conditions with Video Diffusion Models.
Lumiere: compare methods, control or evaluation conditions with Stable Video Diffusion.
Lumiere: compare methods, control or evaluation conditions with From images to video.
Dates & version record
Date displayed for this node: 2024-01-23 · Historical date recorded for the source: 2024-01-23
The timeline uses the initial arXiv submission, distinct from conference publication, model release and the archive addition on 3 October 2026. The account and image refer to v2; its date is recorded in the source history.
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Lumiere: A Space-Time Diffusion Model for Video Generation
https://arxiv.org/abs/2401.12945
Current cited URL
Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited.
Provenance, translation & verification
Archive node #260 · Initial research-paper submission; methods, evaluation and production conditions
Research materials & supplement references · 1
Recent research papers: additions and reconciled sources since 2022 · Read the arXiv abstract, authors and version history, plus the selected figure/page on PDF page 1; proofs and full experiments were not independently audited. · 024
Date as recorded: 2024-01-23
Lumiere: A Space-Time Diffusion Model for Video Generation ↗
Lumiere: A Space-Time Diffusion Model for Video Generation
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
Official material was read within the stated scope; see the source note for reading limits and outstanding checks.
Cite this node
ANTI-AI ARCHIVE. Lumiere: A Space-Time Diffusion Model for Video Generation. Art-history node #260. https://salondesrefuses.cn/en/art-history/347
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.