Project AURIONAI Use-Cases Research & Innovation
image generationfamily

ControlNet

Neural network structure that adds spatial conditioning such as edges, depth or pose to pretrained text-to-image diffusion models.

Stanford UniversityStanford UniversityUSA
Stanford University
Levelfamily
Classimage generation
Parametersnot in the notes
Contextnot in the notes
Released10 Feb 2023
Opennessunknown
Runs onnot in the notes
Statusactive

Lineage

202320242025ControlNet 1.0ControlNet 1.0, Feb 2023ControlNet 1.1ControlNet 1.1, Apr 2023ControlNet Union SDXL 1.0ControlNet Union SDXL 1.0, Jul 2024
ControlNet Union SDXL 1.0 belongs to this familyimage generation7 Jul 20241.26B
Stanford UniversityControlNet 1.1 belongs to this familyimage generation12 Apr 2023
Stanford UniversityControlNet 1.0 belongs to this familyimage generation8 Feb 2023
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Controllable and personalised image generationexemplar

Identity

Developer
Stanford University
Family
not in the notes
Released
10 Feb 2023 sourcesannouncement page
Weights published
–
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
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
ControlNet 1.0 and 1.1 condition Stable Diffusion 1.5 on canny edges, depth, pose, scribbles, segmentation and more; community versions exist for SDXL.
Context length
not in the notes
Input
text, image
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
unknown
Licence
not in the notes sources
Access routes
not in the notes
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/2302.05543 https://arxiv.org/abs/2302.05543
  2. github.com/open-mmlab/mmagic/tree/main/configs/controlnet https://github.com/open-mmlab/mmagic/tree/main/configs/controlnet
  3. aihub.qualcomm.com/models/controlnet_canny https://aihub.qualcomm.com/models/controlnet_canny
  4. arxiv.org/html/2302.05543 https://arxiv.org/html/2302.05543

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "ControlNet", https://aurion.semai.id/models/controlnet-family/, records of October 2026.