Aenica Video Index
← Back to models

Wan-AI / Alibaba

Wan2.2

Active

Wan2.2 is the provider-published open-weight local video family with separate T2V-A14B, I2V-A14B, and unified TI2V-5B checkpoints.

Capabilities

Text-to-videoVaries by variantImage-to-videoVaries by variantVideo-to-videoNoVideo editingNo

Local deployment evidence

The provider-controlled repository publishes local inference code, download commands, and commands for the official T2V, I2V, and TI2V checkpoints.

Hardware entry summary

Lowest documented entry VRAM
24 GB
Applies to
Wan2.2-TI2V-5B

The 24 GB entry point applies only to TI2V-5B; the A14B single-GPU workflows document at least 80 GB.

View full hardware profiles ↓

Local checkpoints

Wan2.2-T2V-A14B

Variant ID: wan2-2-t2v-a14b

Active
Text-to-videoYesImage-to-videoNoVideo-to-videoNoVideo editingNo
Access mode
Local checkpoint
Checkpoint type
Full
Precision
Not specified
Maximum duration
5 seconds
Maximum resolution
720p
Frame rates
Not specified
Aspect ratios
Not specified
Native audio
No
Reference image
No
Pricing
No provider inference fee
View official weights page

Notes

Official local checkpoint. There is no provider inference fee, but hardware, electricity, storage, and processing time still cost money. Apache 2.0 license conditions still apply.

Wan2.2-I2V-A14B

Variant ID: wan2-2-i2v-a14b

Active
Text-to-videoNoImage-to-videoYesVideo-to-videoNoVideo editingNo
Access mode
Local checkpoint
Checkpoint type
Full
Precision
Not specified
Maximum duration
Unknown
Maximum resolution
720p
Frame rates
Not specified
Aspect ratios
Not specified
Native audio
No
Reference image
Yes
Pricing
No provider inference fee
View official weights page

Notes

Official local checkpoint. There is no provider inference fee, but hardware, electricity, storage, and processing time still cost money. Apache 2.0 license conditions still apply.

Wan2.2-TI2V-5B

Variant ID: wan2-2-ti2v-5b

Active
Text-to-videoYesImage-to-videoYesVideo-to-videoNoVideo editingNo
Access mode
Local checkpoint
Checkpoint type
Full
Precision
Not specified
Maximum duration
Unknown
Maximum resolution
720p
Frame rates
24 fps
Aspect ratios
Not specified
Native audio
No
Reference image
Yes
Pricing
No provider inference fee
View official weights page

Notes

Official local checkpoint. There is no provider inference fee, but hardware, electricity, storage, and processing time still cost money. Apache 2.0 license conditions still apply.

Hardware profiles

A14B single-GPU inference

Applies to
Wan2.2-T2V-A14B, Wan2.2-I2V-A14B
Official minimum VRAM
80 GB
Official recommended VRAM
Unknown
Official minimum system RAM
Unknown
Official recommended system RAM
Unknown
Storage
Unknown

The official single-GPU commands for the A14B T2V and I2V models state at least 80 GB VRAM.

Official documentation

TI2V-5B single-GPU inference

Applies to
Wan2.2-TI2V-5B
Official minimum VRAM
24 GB
Official recommended VRAM
Unknown
Official minimum system RAM
Unknown
Official recommended system RAM
Unknown
Storage
Unknown

The official repository states that the TI2V-5B model can run on a consumer-grade GPU with 24 GB VRAM, such as an RTX 4090.

Official documentation

Overview

Provider
Wan-AI / Alibaba
Status
Active
Publication status
Published
Record scope
Family
Release date
2025-07-28
Last verified
2026-08-06

Specifications

Family maximum duration
Varies by variant
Family maximum resolution
720p
Frame rates
Varies by variant
Aspect ratios
Not specified
Portrait support
Unknown
Native audio
No
Reference image
Varies by variant
Character consistency
Unknown

Hardware

Local deployment
Yes
Tested minimum VRAM
Unknown
ComfyUI support
Yes

Licensing

Open weights
Yes
Open source
Yes
Commercial use
Allowed
License
Apache License 2.0

Availability

API availability
Unknown
Web app availability
Unknown

Performance and pricing

Speed category
Unknown
Estimated clip cost
Unknown
Pricing
Free

Best use cases

  • Local text-to-video research
  • Local image-conditioned video generation

Limitations

  • Hardware requirements differ sharply by checkpoint.
  • Aenica has not independently tested minimum VRAM or speed.

Hardware notes

Official single-GPU guidance is 80 GB for A14B workflows and 24 GB for TI2V-5B. These profiles must not be collapsed.

Commercial use notes

The official repository and model cards identify Apache 2.0 licensing. Commercial use is allowed subject to that license; users remain responsible for lawful inputs and outputs.

Speed notes

No Aenica speed category is assigned because no reproducible local benchmark has been completed.

Pricing notes

Local checkpoints have no provider inference fee, but deployment has hardware, electricity, storage, and time costs.

Sources