Image GenerationLow-moderateEstimatedReleased 2024-08-01

Imagen 3 Environmental Impact

Google's latest image generation model

ArchitectureCascaded Diffusion ModelProviderGoogle

One query, in context

Energy, carbon and water for a single use. One 1024x1024 image

Energy2.5Wh per query

About 3.0× a minute of laptop use and 21% of a phone charge.

likely 1.3 Wh – 5.0 Wh
Carbon0.33g per query

About 2.8× a Google search and 16% of 10 m by car.

likely 0.17 g – 0.66 g
Water3mL per query

About 54× a drop of water and 54% of a teaspoon of water.

likely 1 mL – 5 mL
  • Where it runsGoogle global network (64% renewable)
  • Grid carbon intensity300 g CO₂/kWh · 64% renewable
  • Compared with a Google search8x more than a search (0.3 Wh)
  • Water~370 queries to fill 1 litre

Where Imagen 3 sits

#157 of 199 by energy per query. Heavier than 78% of all models. Lit dots are the same kind of model; click any dot to open it.

Google searchKettle boilLLaMA 3.2 1B — 0.03 WhGemini 1.5 Pro — 0.45 WhGPT-4.1 Nano — 0.03 WhGPT-4o — 0.43 WhClaude 3.7 Sonnet — 0.21 WhGPT-4.5 — 1.0 Who3 (Reasoning) — 2.3 WhDeepSeek-R1 — 1.2 WhGrok 2 — 0.50 WhDALL-E 3 — 3.0 WhMidjourney — 7.5 WhStable Diffusion XL — 2.9 WhSora — 500 WhGitHub Copilot — 1.5 WhSuno — 75 WhGPT-4o Mini — 0.04 WhDeepSeek-V3 — 0.24 WhGemini 2.0 Flash — 0.08 WhClaude Opus 4 — 0.39 WhClaude Sonnet 4 — 0.21 WhClaude 3.5 Haiku — 0.06 WhMistral Large 2 — 1.8 WhLLaMA 3.1 70B — 0.38 WhPerplexity AI — 0.50 WhFlux.1 Dev — 3.8 WhVeo 2 — 350 WhGemini 2.5 Pro — 0.40 WhGemini 2.5 Flash — 0.24 WhGPT-4.1 — 0.37 WhGPT-4.1 Mini — 0.03 WhLLaMA 4 Scout — 0.11 WhLLaMA 4 Maverick — 0.11 WhQwen 3 235B — 0.16 WhGrok 3 — 0.40 WhGemma 3 27B — 0.16 WhPhi-4 — 0.09 WhCommand R+ — 0.56 WhGPT-4o Image Generation — 4.5 WhAdobe Firefly — 3.2 WhIdeogram 2.0 — 3.5 WhRunway Gen-3 Alpha — 200 WhKling — 250 WhPika — 180 WhLuma Dream Machine — 160 WhUdio — 70 Who1 — 2.3 Who1-mini — 0.20 Who3-mini — 0.20 Who4-mini — 0.20 WhGPT-4 Turbo — 0.50 WhGemini 1.5 Flash — 0.10 WhGemini Nano — 0.01 WhClaude 3 Opus — 0.56 WhClaude 3 Haiku — 0.06 WhLLaMA 3.1 8B — 0.06 WhLLaMA 3.1 405B — 2.1 WhLLaMA 3.3 70B — 0.38 WhLLaMA 3.2 11B Vision — 0.08 WhLLaMA 3.2 90B Vision — 0.49 WhMistral 7B — 0.06 WhMixtral 8x7B — 0.09 WhMixtral 8x22B — 0.22 WhMistral Small 3 — 0.14 WhCodestral — 0.80 WhAmazon Nova Pro — 0.30 WhAmazon Nova Lite — 0.06 WhAmazon Nova Micro — 0.03 WhERNIE Bot 4.0 — 0.30 WhDoubao Pro — 0.30 WhGLM-4 — 0.19 WhKimi — 0.25 WhJamba 1.5 Large — 1.0 WhStable Diffusion 3.5 — 3.2 WhLeonardo AI — 3.5 WhHaiLuo AI — 220 WhStable Video Diffusion — 150 WhCursor — 1.2 WhAmazon Q Developer — 1.0 WhClaude Code — 2.0 WhWindsurf (Codeium) — 0.80 WhReplit Agent — 1.5 WhWhisper — 0.50 WhOpenAI TTS — 0.30 WhElevenLabs — 1.5 WhNotebookLM Audio Overview — 15 WhClaude Sonnet 4.5 — 0.34 WhClaude Opus 4.5 — 0.42 WhClaude Opus 4.6 — 0.40 WhClaude Sonnet 4.6 — 0.20 WhGPT-5 — 0.44 WhGPT-5 Mini — 0.05 WhGPT-5.2 — 0.61 WhGPT-5.2 Codex — 0.61 WhGPT-5.4 — 0.60 WhGPT-5.4 Mini — 0.03 Who3-pro — 6.0 WhGPT Image 1.5 — 3.8 WhSora 2 — 600 WhGemini 3 Pro — 0.40 WhGemini 3 Flash — 0.15 WhGemini 3.1 Pro — 0.42 WhGemma 3 4B — 0.04 WhGemma 3 12B — 0.08 WhImagen 4 — 2.8 WhVeo 3 — 400 WhVeo 3.1 — 2.4 kWhGrok 4 — 0.60 WhGrok 4.1 — 0.50 WhDeepSeek-R1-0528 — 1.2 WhDeepSeek-V3.1 — 0.24 WhQwen3.5 (397B-A17B) — 0.13 WhQwen3.5 35B-A3B — 0.04 WhMistral Large 3 — 1.5 WhDevstral 2 — 0.60 WhVoxtral TTS — 0.40 WhKimi K2.5 — 0.30 WhGLM-5 — 0.22 WhDoubao 2.0 — 0.30 WhCommand A — 0.60 WhPhi-4 Mini — 0.04 WhPhi-4 Reasoning — 0.27 WhAmazon Nova 2 Pro — 0.35 WhMidjourney V7 — 8.0 WhFlux 2 Pro — 5.0 WhRunway Gen-4.5 — 250 WhKling 3.0 — 280 WhDevin — 3.0 WhElevenLabs v3 — 1.8 WhSuno v5.5 — 80 WhClaude Haiku 4.5 — 0.02 WhGPT-5.3 Codex — 0.45 WhGPT-5.4 Nano — 0.03 WhGPT-OSS 120B — 0.03 WhGPT-OSS 20B — 0.02 WhGemini 3.1 Flash Lite — 0.06 WhLyria 3 Pro — 50 WhDeepSeek-V3.2 — 0.25 WhGrok 4.20 — 0.50 WhQwen3-Coder 480B — 0.20 WhQwen 3.5 Omni — 0.20 WhNemotron 3 Super — 0.45 WhDoubao Seed 2.0 Pro — 0.35 WhSeedance 2.0 — 280 WhGLM-5.1 — 0.22 WhERNIE 5.0 — 0.35 WhMistral Small 4 — 0.40 WhPhi-4 Multimodal — 0.05 WhMidjourney V8 Alpha — 5.0 WhRecraft V4 — 3.0 WhLuma Ray 3 — 200 WhPika 2.5 — 210 WhGPT-5.5 — 0.51 WhGPT-5.5 Instant — 0.06 WhGPT-5.3 Instant — 0.05 WhGPT Image 2 — 5.0 WhClaude Opus 4.7 — 0.44 WhClaude Opus 4.8 — 0.53 WhClaude Fable 5 — 0.79 WhClaude Sonnet 5 — 0.24 WhDeepSeek-V4-Pro — 0.24 WhDeepSeek-V4-Flash — 0.10 WhNano Banana 2 — 1.5 WhQwen3.6 27B — 0.16 WhQwen3.7-Max — 0.45 WhSora 2 Pro — 2.1 kWhClaude Opus 5 — 0.46 WhClaude Fable 5.1 — 0.65 WhClaude Opus 5.5 — 0.45 WhClaude Sonnet 5.5 — 0.24 WhClaude Haiku 5.5 — 0.02 WhClaude Fable 5.2 — 0.60 WhGPT-5.6 Sol — 0.39 WhGPT-5.6 Terra — 0.16 WhGPT-5.6 Luna — 0.05 WhGPT-6 Astra — 0.90 WhGPT-6 Sol — 0.42 WhGPT-6 Luna — 0.06 WhGPT-6 Instant — 0.07 WhGPT-6.1 Sol — 0.42 WhGPT-6.1 Terra — 0.17 WhGemini 3.5 Flash — 0.24 WhGemini 3.5 Flash-Lite — 0.06 WhGemini 3.6 Flash — 0.21 WhGemini 3.7 Flash — 0.14 WhGemini 3.8 Flash — 0.15 WhGemini 4 Argon — 0.45 WhNano Banana 2.1 — 1.5 WhGrok 4.5 — 0.35 WhGrok 4.7 — 0.40 WhMuse Spark — 0.40 WhMuse Spark Open — 0.22 WhKimi K3 — 0.65 WhGLM-5.3 — 0.22 WhQwen3.8-Max — 0.55 WhDeepSeek-V4.1-Flash — 0.10 WhMistral Large 4 — 1.4 WhKling 4.0 — 300 WhSeedance 2.5 — 290 Wh0.1 Wh1 Wh10 Wh100 Wh1 kWhImagen 3

Want something lighter?

What a month of use adds up to

Pick how much you use it. Based on one quick use at a time, five days a week.

Energy
108.3 Wh
Carbon
14.3 g
Water
117 mL

A month of 2 images a day, 5 days a week. The energy is about 9.0× a phone charge and 98% of a kettle boil.

Work out your own →
Energy
270.6 Wh
Carbon
35.7 g
Water
292 mL

A month of 5 images a day, 5 days a week. The energy is about 2.5× a kettle boil and 4% of a UK home's day.

Work out your own →
Energy
1.08 kWh
Carbon
142.9 g
Water
1.17 L

A month of 20 images a day, 5 days a week. The energy is about 9.8× a kettle boil and 15% of a UK home's day.

Work out your own →

How does Imagen 3 compare?

Next to similar models. Bars use a log scale, so each step is a big jump.

Imagen 32.5 Wh

Detailed breakdown

Energy

Imagen 3 consumes approximately 2.5 Wh per image. Running on Google's efficient TPU infrastructure, it benefits from the same hardware optimizations as Gemini, resulting in lower energy consumption than comparable GPU-based image models.

Power source & carbon

Runs on Google's global TPU infrastructure with 100% renewable energy matching and a PUE of 1.10.

Water use

At approximately 2.7 mL per image, Imagen 3 benefits from Google's efficient cooling systems with a site WUE of around 0.26 L/kWh.

About Imagen 3

Imagen 3 is a image generation model from Google, released in August 1, 2024. Google's latest image generation model. Each query uses 2.5 Wh of energy and produces 0.33 g of CO₂. That's 8x the energy of a Google search — reflecting the computational demands of image generation. It ranks in the top quartile of image generation models for energy efficiency (#3 of 19).

Imagen 3 benefits from running in Google Global Network, one of the cleaner grid regions in our dataset at 300 gCO₂/kWh with 64% renewable energy. The same model running in a coal-heavy region would produce significantly more carbon per query.

These figures are estimates derived from hardware specifications and API benchmarks — Google has not published official energy data for Imagen 3. Actual consumption may vary significantly depending on batching, quantisation, and infrastructure optimisations that we cannot observe from outside.

Imagen 3 in context

22.8 kWhper year

Your yearly Imagen 3 footprint

At 25 queries per day, your annual Imagen 3 usage consumes 22.8 kWh — roughly what a fridge uses in a month. That produces 3.0 kg of CO₂.

8xvs a text query

Image vs text: the energy gap

Generating one image with Imagen 3 uses 8x more energy than a text conversation with ChatGPT. The diffusion process that creates images requires many iterative passes through the model, each refining the image from noise — far more compute per output than generating text one token at a time.

What does your Imagen 3 usage cost the planet?

Use the calculator to estimate your personal footprint based on how often you use Imagen 3.

Calculate my compute

Frequently asked questions

How much energy does Imagen 3 use per query?

Each Imagen 3 query consumes approximately 2.5 Wh of energy. This is 8x more than a traditional Google search (~0.3 Wh).

What is Imagen 3's carbon footprint?

Based on the carbon intensity of Google global network (64% renewable), each query produces approximately 0.33 g of CO2. The grid in this region has a carbon intensity of 300 g CO2/kWh with 64% renewable energy.

How much water does Imagen 3 use?

Each query consumes approximately 3 mL of water, primarily used for cooling the data centers that process the request.

How does Imagen 3 compare to a Google search?

A Imagen 3 query uses 8x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Imagen 3 uses 2.5 Wh.

Technical details

Architecture
Cascaded Diffusion Model
Release date
2024-08-01
Open source
No

Sources