image generation
Colorful Image Colorization
CNN that predicts plausible colours for grayscale photos.
Levelmodel
Classimage generation
Parametersnot in the notes
Contextnot in the notes
Released28 Mar 2016
Opennessunknown
Runs onnot in the notes
Statusactive
R&D Topics
Runtimes
Identity
- Developer
- UC Berkeley
- Family
- not in the notes
- Released
- 28 Mar 2016 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
- CNN
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- OpenVINO Open Model Zoo ships colorization-siggraph and colorization-v2.
- Context length
- not in the notes
- Input
- 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
- 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
- OpenVINO
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.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperUC Berkeleyuniversity, USA
UC Berkeleyuniversity, USAModelColorful Image ColorizationUC Berkeley, image generation
Colorful Image ColorizationUC Berkeley, image generationR&D TopicsGenerative Image Modelling Methods (GANs, Diffusion and Image Translation)Image and Video Restoration and Super-Resolution
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
R&D topics 2
Image and Video Restoration and Super-ResolutionRemoving blur, noise and compression damage and raising the resolution of photos and vide…produced byGenerative Image Modelling Methods (GANs, Diffusion and Image Translation)Core methods for learning to generate or translate images, from GANs and autoencoders to…produced by
Sources
- arxiv.org/abs/1603.08511 https://arxiv.org/abs/1603.08511
- github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/colorization-siggraph
- arxiv.org/html/1603.08511 https://arxiv.org/html/1603.08511
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Colorful Image Colorization", https://aurion.semai.id/models/colorization-zhang/, records of October 2026.