Energy for generating one image with a text-to-image model. Each entry records the claim as published: what it counts, who made it and who paid,
and any dispute. Figures with different boundaries are not comparable without reading what each counts.
Least efficient open image generation model, Power Hungry Processing
11.49 Wh per image generated (published as: 11.49 kWh for 1,000 inferences; converted from kWh per 1,000 to Wh per one)
whereas the least efficient image generation model uses as much energy as 522 smartphone charges (11.49 kWh), or around half a charge per image generation
1,000 image generations, run sequentially without batching, with the least efficient of the eight image generation models tested
Scope
servers
Counts
GPU, CPU and RAM energy measured with Code Carbon
Leaves out
not stated
Model or version
not stated (the sentence does not name the model)
Place
AWS us-west-2 (Oregon)
Period measured
not stated
Method
Each model ran 1,000 inferences on each of three datasets, ten times, on a node of 8 NVIDIA A100-SXM4-80GB GPUs, with energy measured by the Code Carbon package.
Claimed by
Company: Alexandra Sasha Luccioni, Yacine Jernite (Hugging Face) and Emma Strubell (Carnegie Mellon University)
Paid for by
not stated
Dispute
none
History
Added.
Mean image generation across open text-to-image models, Power Hungry Processing
a mean of 2.907 Wh per image generated (published as: 2.907 kWh per 1,000 queries (Table 2; the text rounds it to 2.9kWh); converted from kWh per 1,000 to Wh per one)
Table 2. Mean and standard deviation of energy per 1,000 queries for the ten tasks examined in our analysis. ... to the most energy-intensive one, image generation, whose mean consumption is 2.9kWh.
1,000 image generations, run sequentially without batching, on prompts from each of three datasets (DiffusionDB, ImageReward, SD Prompts)
Scope
servers
Counts
GPU, CPU and RAM energy measured with Code Carbon
Leaves out
not stated
Model or version
Eight text-to-image models (stable-diffusion-v1-4, v1-5, 2-1 and xl-base-1.0, openjourney, dreamlike-photoreal-2.0, bk-sdm-tiny, tiny-sd), per the paper's Table 6
Place
AWS us-west-2 (Oregon)
Period measured
not stated
Method
Each model ran 1,000 inferences on each of three datasets, ten times, on a node of 8 NVIDIA A100-SXM4-80GB GPUs, with energy measured by the Code Carbon package.
Claimed by
Company: Alexandra Sasha Luccioni, Yacine Jernite (Hugging Face) and Emma Strubell (Carnegie Mellon University)
Paid for by
not stated
Dispute
none
The calculator uses this figure: AI image (mean of eight open models, one at a time on GPU servers, 2024 benchmark).
History
Added.
Stable Diffusion 3 Medium 1024 × 1024 image, GPU energy only (MIT Technology Review)
0.317 Wh per image generated (1024 × 1024 pixels, standard quality) (published as: about 1,141 joules of GPU energy; converted from J to Wh)
Generating a standard-quality image (1024 x 1024 pixels) with Stable Diffusion 3 Medium, the leading open-source image generator, with 2 billion parameters, requires about 1,141 joules of GPU energy.
One standard-quality 1024 × 1024 image from Stable Diffusion 3 Medium (2 billion parameters)
Scope
servers
Counts
GPU energy
Leaves out
CPUs, fans and other equipment
Model or version
Stable Diffusion 3 Medium
Place
not stated
Period measured
not stated
Method
GPU energy measured by Jae-Won Chung (University of Michigan, ML.Energy) for the article.
Claimed by
Independent: MIT Technology Review (James O'Donnell and Casey Crownhart)
Paid for by
Tarbell Center for AI Journalism (grant)
Dispute
none
History
Added.
Stable Diffusion 3 Medium 1024 × 1024 image, estimated total energy (MIT Technology Review)
0.634 Wh per image generated (1024 × 1024 pixels, standard quality) (published as: an estimated 2,282 joules total; converted from J to Wh)
With diffusion models, unlike large language models, there are no estimates of how much GPUs are responsible for the total energy required, but experts suggested we stick with the “doubling” approach we’ve used thus far because the differences are likely subtle. That means an estimated 2,282 joules total.
One standard-quality 1024 × 1024 image from Stable Diffusion 3 Medium (2 billion parameters)
Scope
data centre
Counts
GPU energy; an estimate for CPUs, fans and other equipment (GPU energy doubled)
Leaves out
not stated
Model or version
Stable Diffusion 3 Medium
Place
not stated
Period measured
not stated
Method
GPU energy measured by Jae-Won Chung (University of Michigan, ML.Energy), then doubled to estimate the whole operation, following a 2024 Microsoft paper on LLM inference.
Claimed by
Independent: MIT Technology Review (James O'Donnell and Casey Crownhart)
Paid for by
Tarbell Center for AI Journalism (grant)
Dispute
none
History
Added.
Stable Diffusion 3 Medium image at 50 diffusion steps (MIT Technology Review)
1.223 Wh per image generated (1024 × 1024 pixels, 50 diffusion steps) (published as: about 4,402 joules; converted from J to Wh)
Improving the image quality by doubling the number diffusion steps to 50 just about doubles the energy required, to about 4,402 joules.
One higher-quality 1024 × 1024 image from Stable Diffusion 3 Medium, with the number of diffusion steps doubled to 50
Scope
data centre
Counts
not stated
Leaves out
not stated
Model or version
Stable Diffusion 3 Medium
Place
not stated
Period measured
not stated
Method
Measured by Jae-Won Chung (University of Michigan, ML.Energy) for the article; the sentence follows the doubled 2,282 J total but does not say explicitly whether 4,402 J includes the doubling for non-GPU energy.
Claimed by
Independent: MIT Technology Review (James O'Donnell and Casey Crownhart)