Project AURIONAI Use-Cases Research & Innovation
Alibaba (Qwen)
video generation

Wan 2.1 T2V 1.3B

Smallest Wan 2.1 text-to-video model, offered in Amazon SageMaker JumpStart.

Alibaba (Qwen)Alibaba (Qwen)ChinaWanFamily
Table of Wan-Bench scores for Wan 2.1 1.3B and 14B against other video models.
Levelvariant
Classvideo generation
Parameters1.42B
Contextnot in the notes
Released25 Feb 2025
Opennessopen weights permissive
Runs onconsumer GPU
Statusactive

Lineage

successorproduct of
Wan 2.1 to Wan 2.2: successor, medium confidenceWan 2.1 to Wan 2.1 T2V 1.3B: product of, medium confidenceWan 2.1Wan 2.1Alibaba (Qwen), 2025Wan 2.1 T2V 1.3BWan 2.1 T2V 1.3BAlibaba (Qwen), Feb 2025Wan 2.2Wan 2.2Alibaba (Qwen), Jul 2025
Alibaba (Qwen)Wan 2.1 is the parent (product of)medium confidencemodel card
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, 3 models. Confidence and evidence are the notes' own.

R&D Topics

Text-to-video foundation modelsproduced by

Identity

Developer
Alibaba (Qwen)
Family
Wan
Released
25 Feb 2025 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
diffusion
Total parameters
1.42B sources
Active parameters
–
Checkpoint parameters
–
Note
Parameter count from the Hugging Face safetensors total.
Context length
not in the notes
Input
text
Output
video
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, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
consumer GPU
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. huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers
  2. arxiv.org/abs/2503.20314 https://arxiv.org/abs/2503.20314
  3. jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
  4. github.com/Wan-Video/Wan2.1 https://github.com/Wan-Video/Wan2.1

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Wan 2.1 T2V 1.3B", https://aurion.semai.id/models/alibaba-wan-2-1-t2v-1-3b/, records of October 2026.