Project AURIONAI Use-Cases Research & Innovation
multimodal LLMfamily

Janus

Unified models that both understand and generate images, using separate visual encoding paths for the two jobs inside one transformer.

DeepSeekDeepSeekChina
DeepSeek
Levelfamily
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released17 Oct 2024
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

202420252026Janus 1.3BJanus 1.3B, Oct 2024JanusFlow 1.3BJanusFlow 1.3B, Nov 2024Janus-Pro 1BJanus-Pro 1B, Jan 2025Janus-Pro 7B, Jan 2025
DeepSeekJanus-Pro 1B belongs to this familymultimodal LLM29 Jan 2025
DeepSeekJanus-Pro 7B belongs to this familymultimodal LLM29 Jan 2025
DeepSeekJanusFlow 1.3B belongs to this familymultimodal LLM12 Nov 20242.05B
DeepSeekJanus 1.3B belongs to this familymultimodal LLM18 Oct 20242.09B
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

Omni-modal and unified multimodal modelsexemplar

Identity

Developer
DeepSeek
Family
not in the notes
Released
17 Oct 2024 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
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text, image
Output
text, 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
MIT License 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/2410.13848 https://arxiv.org/abs/2410.13848
  2. github.com/deepseek-ai/Janus https://github.com/deepseek-ai/Janus
  3. huggingface.co/api/models?pipeline_tag=any-to-any&sort=likes... https://huggingface.co/api/models?pipeline_tag=any-to-any&sort=likes&limit=50
  4. kaggle.com/models/deepseek-ai/janus-pro https://www.kaggle.com/models/deepseek-ai/janus-pro
  5. huggingface.co/deepseek-ai/Janus-1.3B https://huggingface.co/deepseek-ai/Janus-1.3B
  6. huggingface.co/deepseek-ai/Janus-Pro-1B https://huggingface.co/deepseek-ai/Janus-Pro-1B

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