Stable Diffusion 1.4

Open weights Ludwig Maximilian University of Munich August 2022

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Ludwig Maximilian University of Munich
Organisation type
Academia
Country
Germany
Published
22 August 2022
Authors
Robin Rombach, Patrick Esser

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Image generation
Task
Image generation, Text-to-image
Base model
Stable Diffusion 1.2

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

225k steps at 512x512 on "laion-aesthetics v2 5+", with 10% dropping of text conditioning. Batch: 32 x 8 x 2 x 4 = 2048

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
5 × 10²² FLOP

312000000000000 FLOP / GPU / sec * 150000 GPU-hours * 3600 sec / hour * 0.3 [assumed utilization] = 5.0544e+22 FLOP https://github.com/CompVis/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100 PCIe
Chips used
256
Power draw
153.9 kW

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Open — downloadable
Model access
Open weights (restricted use)
Training code
Open (restricted use)

OpenRAIL license for weights https://huggingface.co/CompVis/stable-diffusion-v1-4 "The Responsible AI License allows users to take advantage of the model in a wide range of settings (including free use and redistribution) as long as they respect the specific use case restrictions outlined, which correspond to model applications the licensor deems ill-suited for the model or are likely to cause harm" Open RAIL-M license https://github.com/CompVis/stable-diffusion

Hugging Face
CompVis

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Stable Diffusion v1-4 Model Card
Last updated
28 November 2025

What the numbers mean

Where it came from

Stable Diffusion 1.4 was published by Ludwig Maximilian University of Munich, in the country recorded as Germany, during August 2022. The category the publisher falls under is academia.

It works in the domain of Image generation, and is recorded as performing the task of image generation, Text-to-image.

Rather than being trained from scratch, it is derived from Stable Diffusion 1.2. That is why it shares the base model's general shape and size.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. On Hugging Face it is published under the organisation CompVis.

Training and provenance

Producing it required arithmetic totalling around 5 × 10²² FLOP, on hardware recorded as NVIDIA A100 PCIe. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

Stable Diffusion 1.4 — common questions

01

Stable Diffusion 1.4— is it open source?

Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

02

Stable Diffusion 1.4— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

03

Stable Diffusion 1.4— who created it?

It was published by Ludwig Maximilian University of Munich, based in Germany, an organisation categorised as academia.

04

Stable Diffusion 1.4— when was it released?

It was published in August 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

Stable Diffusion 1.4— what is it used for?

It works in the domain of Image generation, and is recorded as handling the task of image generation, Text-to-image. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

06

Stable Diffusion 1.4— where can I download it?

Its weights are published on Hugging Face, under the organisation CompVis. We do not host model files — this site calculates what hardware is needed to run them.

07

Stable Diffusion 1.4— how much compute was used to train it?

Training consumed around 5 × 10²² FLOP, on hardware recorded as NVIDIA A100 PCIe. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

08

Stable Diffusion 1.4— what GPU do I need to run it?

We cannot say. It has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.