Computational Model Studio · Model release
Wan2.2 T2V-A14B
Generate 5-second video clips from text prompts using publisher-distributed Wan2.2 T2V weights.
Developer: Wan-AI · Last verified:
What it is designed to do
Generate 5-second video clips from text prompts using publisher-distributed Wan2.2 T2V weights.
Documented uses: Generate 5-second video clips from text prompts using publisher-distributed Wan2.2 T2V weights.
Access and deployment
- Wan2.2 T2V-A14B publisher weights — available. Publisher repository lists model files for download. Artifact documentation
- workstation local: GPU with at least 80 GB VRAM; 80 GB VRAM; Publisher single-GPU T2V-A14B command with offload_model and convert_model_dtype for a 5-second 720p video. (publisher stated requirement) Limits: The publisher warns that out-of-memory runs may require additional offloading options; this is not a measured result on a named consumer GPU..
Technical profile and review notes
- Construction
- learned
- Representation
- neural
- Normalized architecture tags
- No normalized architecture tag assigned
- Lifecycle
- active
Inclusion rationale: A separately distributed text-to-video model gives visitors a weights access route alongside hosted video services.
Limitations
- The publisher’s described output is recorded as the exact media form shown; surrounding editing tools or orchestration are not attributed to this model.
- Weight access alone does not establish a measured local deployment profile.
Sources and related Studio records
Sources
Connections
- In areaComputational Models
- Supports functionGenerate video
- ArtifactWan2.2 T2V-A14B publisher weights