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

Wan 2.2 TI2V-5B

5B text-and-image-to-video Wan 2.2 model.

Alibaba (Qwen)Alibaba (Qwen)ChinaWan 2.2Family
High-compression Wan2.2-VAE used by TI2V-5B, from the model card.
Levelmodel
Classvideo generation
Parameters5B
Contextnot in the notes
Released28 Jul 2025
Opennessopen weights permissive
Runs onconsumer GPU
Statusactive

R&D Topics

Text-to-video foundation modelsproduced by

Identity

Developer
Alibaba (Qwen)
Family
Wan 2.2
Released
28 Jul 2025 sourcessecondary report
Weights published
–
Record checked
10 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
5B sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text, image
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
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.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. atlascloud.ai/de/blog/tips/is-wan-3.0-open-source https://www.atlascloud.ai/de/blog/tips/is-wan-3.0-open-source
  2. Text-to-Video Models – Hugging Face huggingface.co https://huggingface.co/models?pipeline_tag=text-to-video&sort=trending

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Wan 2.2 TI2V-5B", https://aurion.semai.id/models/alibaba-wan-2-2-ti2v-5b/, records of October 2026.