Image GenerationLow-moderatePeer-reviewedReleased 2023-07-26

Stable Diffusion XL Environmental Impact

Open-source image model — higher energy per image

ArchitectureLatent Diffusion Model (U-Net based)Parameters6.6BProviderStability AI

One query, in context

Energy, carbon and water for a single use. One 1024x1024 image (30 steps, standard settings)

Energy2.9Wh per query

About 3.5× a minute of laptop use and 24% of a phone charge.

likely 1.9 Wh – 4.3 Wh
Carbon1.2g per query

About 10× a Google search and 57% of 10 m by car.

likely 0.80 g – 1.8 g
Water5mL per query

About 1.1× a teaspoon of water and 2% of a glass of water.

likely 4 mL – 8 mL
  • Where it runsSelf-hosted (varies)
  • Grid carbon intensity458 g CO₂/kWh · 32% renewable
  • Compared with a Google search10x more than a search (0.3 Wh)
  • Water~185 queries to fill 1 litre

Where Stable Diffusion XL sits

#159 of 199 by energy per query. Heavier than 79% 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 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 WhImagen 3 — 2.5 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 kWhStable Diffusion XL

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
125.6 Wh
Carbon
52.0 g
Water
234 mL

A month of 2 images a day, 5 days a week. The energy is about 1.1× a kettle boil and 2% of a UK home's day.

Work out your own →
Energy
313.9 Wh
Carbon
129.9 g
Water
585 mL

A month of 5 images a day, 5 days a week. The energy is about 2.9× a kettle boil and 4% of a UK home's day.

Work out your own →
Energy
1.26 kWh
Carbon
519.6 g
Water
2.34 L

A month of 20 images a day, 5 days a week. The energy is about 11× a kettle boil and 17% of a UK home's day.

Work out your own →

How does Stable Diffusion XL compare?

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

Stable Diffusion XL2.9 Wh

Detailed breakdown

Energy

Stable Diffusion XL consumes approximately 2.9 Wh per image at standard settings (30 steps, 1024x1024) based on the Luccioni et al. benchmark on A100 hardware. High-quality configurations (50+ steps, upscaling) can reach 11+ Wh. Being open-source, it's often run on consumer GPUs which may be less power-efficient than data center hardware.

Power source & carbon

As an open-source model, Stable Diffusion XL is deployed across diverse infrastructure — personal PCs, cloud providers (RunPod, Replicate, AWS, etc.), and on-premises servers. The carbon impact varies enormously. A user running it on a home PC in Sweden (30 g CO2/kWh) produces roughly 25x less carbon than someone running it on a cloud server in India (700 g CO2/kWh). Stability AI's own hosted service has faced financial difficulties and defaulted on payments to AWS and Google Cloud.

Water use

Water consumption is approximately 5.4 mL per image when run in a data center. When run locally on a personal computer, water consumption for cooling is effectively zero since PCs use air cooling. This is one of the key environmental advantages of self-hosted open-source models.

About Stable Diffusion XL

Stable Diffusion XL is an open-source image generation model from Stability AI, released in July 26, 2023, that runs below the category average for energy consumption at 2.9 Wh per query. Because its weights are publicly available, it can be self-hosted on any infrastructure — meaning its carbon footprint depends entirely on where and how you choose to run it. At 6.6B parameters, it open-source image model — higher energy per image.

Stable Diffusion XL in context

26.5 kWhper year

Your yearly Stable Diffusion XL footprint

At 25 queries per day, your annual Stable Diffusion XL usage consumes 26.5 kWh — roughly what a fridge uses in a month. That produces 10.9 kg of CO₂.

10xvs a text query

Image vs text: the energy gap

Generating one image with Stable Diffusion XL uses 10x 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.

Key insights

  • Open-source weights — can be self-hosted on infrastructure you control

The Stability AI Stable family

One chart per tier, on a shared time axis. Hover a dot for details; click to open that version.

Stable Diffusion XL: 2.9 Wh · Jul 2023Stable Diffusion XL2.9 WhStable Video Diffusion: 150.0 Wh · Nov 2023Stable Video Diffusion150.0 WhStable Diffusion 3.5: 3.2 Wh · Oct 2024Stable Diffusion 3.53.2 WhJul 2023Oct 2024
Stable Diffusion XL to Stable Diffusion 3.5: 10% higher energy per query across 3 versions.

What does your Stable Diffusion XL usage cost the planet?

Use the calculator to estimate your personal footprint based on how often you use Stable Diffusion XL.

Calculate my compute

Frequently asked questions

How much energy does Stable Diffusion XL use per query?

Each Stable Diffusion XL query consumes approximately 2.9 Wh of energy. This is 10x more than a traditional Google search (~0.3 Wh).

What is Stable Diffusion XL's carbon footprint?

Based on the carbon intensity of Self-hosted (varies), each query produces approximately 1.2 g of CO2. The grid in this region has a carbon intensity of 458 g CO2/kWh with 32% renewable energy.

How much water does Stable Diffusion XL use?

Each query consumes approximately 5 mL of water, primarily used for cooling the data centers that process the request.

How does Stable Diffusion XL compare to a Google search?

A Stable Diffusion XL query uses 10x more than a Google search in terms of energy. A Google search uses approximately 0.3 Wh, while Stable Diffusion XL uses 2.9 Wh.

Technical details

Architecture
Latent Diffusion Model (U-Net based)
Parameters
6.6B
Release date
2023-07-26
Open source
Yes

Sources