Video Generation

Luma Dream Machine Environmental Impact

ExtremeEstimated

Fast video generation from text and images

Architecture
Transformer-based video model
Provider
Luma AI
160.0 Wh
Energy per query
56.0 g
CO₂ per query
296 mL
Water per query
533x more than
vs Google search

Energy per query

160.0 Wh

533x more than a Google search (0.3 Wh)

CO2 per query

56.0 g

US East (Virginia) grid (450 gCO₂/kWh)

Water per query

296 mL

~3 queries to fill 1 litre

Processing location

Cloud (US)

Provider

Luma AI

Category

Video Generation

Grid carbon intensity

450 g CO2/kWh (25% renewable)

How does Luma Dream Machine compare?

Ranked #138 of 152 models by energy per query

0 Wh150 Wh300 Wh450 Wh600 WhLuma DreamMachineRunway Gen-3AlphaVeo 2SoraGoogle search (0.3 Wh)

Detailed Breakdown

Energy Consumption

Luma Dream Machine generates video clips estimated at ~160 Wh per generation. It's known for faster generation times (often under 2 minutes), which generally translates to lower energy per clip than slower models like Sora.

Power Source & Carbon

Luma AI runs on US-based cloud infrastructure. No environmental disclosures published.

Water Usage

Estimated at ~296 mL per clip based on energy and typical cloud WUE.

About Luma Dream Machine

Luma Dream Machine sits at the high end of AI energy consumption at 160.0 Wh per generating one short video clip — over 533x what a Google search uses. Luma AI's video generation model, released in June 12, 2024, fast video generation from text and images. The extreme energy cost reflects the computational complexity of video generation: generating coherent frames across both space and time.

These figures are estimates derived from hardware specifications and API benchmarks — Luma AI has not published official energy data for Luma Dream Machine. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

Luma Dream Machine in Context

13x
phone charges per video

The video generation premium

One Luma Dream Machine generation uses 160.0 Wh — the equivalent of 13 full smartphone charges. Video generation requires running a diffusion model across both spatial and temporal dimensions, making it fundamentally more compute-intensive than text or image tasks. This is not an efficiency problem to be solved; it is an inherent characteristic of the task.

What does your Luma Dream Machine usage cost the planet?

Use our calculator to estimate your personal environmental footprint based on how often you use Luma Dream Machine.

Calculate My Compute

Frequently Asked Questions

How much energy does Luma Dream Machine use per query?

Each Luma Dream Machine query consumes approximately 160.0 Wh of energy. This is 533x more than a traditional Google search (~0.3 Wh).

What is Luma Dream Machine's carbon footprint?

Based on the carbon intensity of Cloud (US), each query produces approximately 56.0 g of CO2. The grid in this region has a carbon intensity of 450 g CO2/kWh with 25% renewable energy.

How much water does Luma Dream Machine use?

Each query consumes approximately 296 mL of water, primarily used for cooling the data centers that process the request.

How does Luma Dream Machine compare to a Google search?

A Luma Dream Machine query uses 533x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Luma Dream Machine uses 160.0 Wh.

Technical Details

Architecture

Transformer-based video model

Release date

2024-06-12

Open source

No