Model profile

Lumiere AI video generator

Google Research's space-time diffusion research model for realistic video generation and editing.

Should You Use Lumiere?

Use it for: research history, space-time diffusion context, video editing research

Skip or compare first if: Research-only. Do not include in consumer availability ranking.

Positioning: Google Research's space-time diffusion research model for realistic video generation and editing.

Top Capabilities

  • Space-time diffusionLumiere uses a space-time diffusion model for video generation.Source
  • Primary source-backed profileLumiere has an official source, repository, paper, or model card attached for verification.Source
  • Workflow coverageLumiere is tracked for t2v, i2v, stylization workflows in the catalogue.Source

Company Snapshot

Built by Google Research

Founded / HQ: partial/evidence pending / United States

What it does: Google Research is Google's broad research organization; Lumiere is a research-only video generation project relevant to the history of text-to-video and image-to-video systems. confirmed

Main products/ecosystem: Lumiere confirmed

Founders/leadership: partial/evidence pending confirmed

Scale/funding/status: corporate research team, United States confirmed

Relationship to Lumiere: Lumiere should be presented as a historical research reference, not as a tool that consumers can choose for everyday generation.

No public source link is attached yet.

Price, Access, Open Status

Access: Research Only

Open/closed: Closed. No official open weights are listed in the current profile.

Not publicly available as a consumer product.

Price, regional access, and commercial terms need a live check before cost-sensitive recommendations.

No public source link is attached yet.

No public source link is attached yet.

Latest Version

Lumiere

2024-01 / confirmed

Research project page and arXiv paper released.

Latest News

Lumiere

2024-01 / Google Research

External source link for this model.

Open original

Why It Ranks Here

Rank: #41 50

Score source: Provisional quality proxy based on official/research evidence and catalogue presence; exact external rank requires live leaderboard/API collection.. Evidence confidence is medium.

Rankings Methodology

Key Score Drivers

These are the scoring dimensions most responsible for the current ranking position.

  • Model Quality Proxy: 68Provisional quality proxy based on official/research evidence and catalogue presence; exact external rank requires live leaderboard/API collection.
  • Capability Depth: 65Supported workflow tags: t2v, i2v, stylization, inpainting, research_only. Depth rewards T2V/I2V/V2V, references, native audio, editing, API, and open weights where present.
  • Ecosystem Popularity: 54GitHub stars are not applicable to this closed or research-only product unless an official public model repository is confirmed.

    No public source link is attached yet.

  • Web Authority: 52SEO snapshot found product domain lumiere-video.github.io and company domain research.google; sampled sitemap URL count is 0.

Alternatives And Comparisons

Use these when price, access, output style, or workflow fit is uncertain.

  • SeedanceByteDance's frontier video generation family for multimodal, audio-video, short-form, and cinematic creator workflows.View modelCompare
  • KlingKuaishou's broad AI video and image generation platform for text-to-video, image-to-video, native audio, references, and creator effects.View modelCompare
  • PixVerseA creator-friendly AI video platform with strong API coverage for text-to-video, image-to-video, transitions, extension, and reference fusion.View modelCompare
  • ViduShengShu Technology's video model family for native audio-video storytelling, image-to-video, and scene-oriented short-form production.View modelCompare

What It Is

Primary content is rendered into static HTML.

Lumiere is a Google Research video generation project based on space-time diffusion. It is not a consumer product, but it is important in the technical history of video generation because it addressed temporal consistency, stylization, cinemagraphs, and video inpainting.

Version Progress

Open / Source Evidence

Status: Closed

No official open weights are listed in the current profile.

Latest News

Model-specific news entries link directly to the original publisher; article bodies stay off-site.

Full Score Breakdown

Weighted evidence dimensions separate model quality from access, web authority, ecosystem, and source confidence. See methodology and rankings.

DimensionScoreWeightEvidenceConfidence
Model Quality Proxy 68 24% Provisional quality proxy based on official/research evidence and catalogue presence; exact external rank requires live leaderboard/API collection. medium
Missing: live Artificial Analysis rank/Elo by modality, live Arena AI rank/score by modality
Capability Depth 65 16% Supported workflow tags: t2v, i2v, stylization, inpainting, research_only. Depth rewards T2V/I2V/V2V, references, native audio, editing, API, and open weights where present. high
Missing: hands-on feature verification, mode-specific limits by duration/resolution
Access And Pricing 6 12% Access types: research_only. Pricing note: Not publicly available as a consumer product. low
Missing: current free tier, normalized price per video minute
Version Maturity 38 12% 1 version/history entries in the profile; latest public date is 2024-01. medium
Missing: automated release-note monitor, model ID/version mapping across providers
Ecosystem Popularity 54 10% GitHub stars are not applicable to this closed or research-only product unless an official public model repository is confirmed.

No public source link is attached yet.

medium
Missing: GitHub: n/a for closed-source model
Web Authority 52 10% SEO snapshot found product domain lumiere-video.github.io and company domain research.google; sampled sitemap URL count is 0. medium
Missing: Similarweb/API traffic, Tranco rank
Company Distribution 20 10% Google Research distribution profile: Lumiere should be presented as a historical research reference, not as a tool that consumers can choose for everyday generation.. medium
Missing: app store ratings/review volume, product MAU/traffic
Source Confidence 83 6% Profile source confidence is confirmed with 2 official URL(s), 1 feature evidence item(s), SEO present, GitHub n/a. high
Missing: paid/API evidence refresh, manual output review artifacts

Limitations And Pricing

Not publicly available as a consumer product.

  • Research-Only.
  • Do Not Include In Consumer Availability Ranking.