Project AURIONAI Use-Cases Research & Innovation
LMU Munich
image generation

Latent Diffusion (LDM)

Diffusion in the latent space of a pretrained autoencoder, the method behind Stable Diffusion.

LMU MunichLMU MunichGermanyRunwayRunwayUSA
Figure from the Latent Diffusion (LDM) paper: Illustrating perceptual and semantic compression: Most bits of a digital image correspond to imperceptible details.
Levelmodel
Classimage generation
Parametersnot in the notes
Contextnot in the notes
Released20 Dec 2021
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

successor
Latent Diffusion (LDM) to Stable Diffusion: successor, medium confidenceLatent Diffusion (LDM)Latent Diffusion (LDM)LMU Munich, Dec 2021Stable DiffusionStable DiffusionStability AI
Stability AIStable Diffusion is a child (successor)medium confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Generative image modelling methods (GANs, diffusion and image translation)exemplar

Identity

Developer
LMU Munich, Runway
Family
not in the notes
Released
20 Dec 2021 sourcesannouncement page
Weights published
18 Jul 2022
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
diffusion
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2112.10752 https://arxiv.org/abs/2112.10752
  2. huggingface.co/CompVis/ldm-text2im-large-256 https://huggingface.co/CompVis/ldm-text2im-large-256
  3. huggingface.co/api/models?pipeline_tag=unconditional-image-g... https://huggingface.co/api/models?pipeline_tag=unconditional-image-generation&sort=downloads&limit=50
  4. arxiv.org/html/2112.10752 https://arxiv.org/html/2112.10752

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Latent Diffusion (LDM)", https://aurion.semai.id/models/latent-diffusion-ldm/, records of October 2026.