CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.video / Wan2.2-T2V-A14B
From: Wan-AI <huggingface.co/Wan-AI>Newsgroups: alt.freeweights.videoSubject:

Wan2.2-T2V-A14B

Date: 2026-11-14Commit: c8c270bSigned: 2DC28CC7B26A283B ✓

Text to video model. Safetensors weights, 126 GB in all. Published by Wan-AI under Apache-2.0.

video126GBWan2.2-T2V-A14Bsafetensorspermissive
FactsParamsnot statedSize126 GBFormatssafetensorsTasktext to videoLicenseApache-2.0From sourcepermissive
$ fw get Wan-AI/Wan2.2-T2V-A14B
# manifest sha256 7b4e1517047a… · 126 GB · 32 files
$ fw verify ./Wan2.2-T2V-A14B Wan-AI/Wan2.2-T2V-A14B
From sourceWan-AI/Wan2.2-T2V-A14BLast check: 2026-11-14 15:36 UTC
Runs withComfyUI
OverviewFilesUse itLicenseProvenance

Overview

Size
126 GB
Weights
114 GB (safetensors)
Parameters
not stated
Formats
safetensors
Task
text to video
License
Apache-2.0 (permissive)
Files
32, each with a sha256
Publisher
Wan-AI
Added
2026-11-14
Section
alt.freeweights.video
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-14 15:36 UTCpassed

Files

32 files · 126 GBWeights 114 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 32 files with their sha256
FileSizesha256
.gitattributes1.81 KB01369ba77d127c65ffca67c40fe3b9bc6941adf37baf351ce80b1f1df3b702bc
README.md17.2 KB45aca8eac89096edafa083cd12b4842a696317c318cdfdfd7b1ce4a5840d537f
Wan2.1_VAE.pth508 MB38071ab59bd94681c686fa51d75a1968f64e470262043be31f7a094e442fd981
assets/comp_effic.png202 KB75ee012dcfb08365bec67a3ec7afc126fc2817f79b9f80e38711792d4770e32b
assets/logo.png56.3 KB96cddc0f667293436d0b9f92a299b6346b65b231d38ee49719a33d46c91fe1e3
assets/moe_2.png528 KB4ea471ccb64349bd08bc9a78f336ae000e9ca3b40da9a652b8028b214a8c6093
assets/moe_arch.png74.9 KB709510625af90bad3f9509c8c9bb6dc779576cd7f80b9bc95d75fe33f2755079
assets/performance.png307 KB97ef99c13c8ae717a8a11c8d8ec927b69077c647cc6689755d08fc38e7fbb830
assets/vae.png165 KB4aaea5e187f1c5908e15ade5bef24c9fb59882986bc3d2ad75f7fe820f3d772f
configuration.json47 B5d1cc0f912402522f05f12a681278da402004ad37006c72ecbb461c50065ec6c
google/umt5-xxl/special_tokens_map.json6.62 KB7b8a9f5040adb67b5805abdfd42c1f8d0f3d0e711f10726580eb3789cd0ad61d
google/umt5-xxl/spiece.model4.55 MBe3909a67b780650b35cf529ac782ad2b6b26e6d1f849d3fbb6a872905f452458
google/umt5-xxl/tokenizer.json16.8 MB6e197b4d3dbd71da14b4eb255f4fa91c9c1f2068b20a2de2472967ca3d22602b
google/umt5-xxl/tokenizer_config.json61.7 KBed9a3a8b0faa71a70a32847e0435fe036e6e112d4df4edb7bb48a921e344dc05
high_noise_model/config.json250 B691a47e123c3dd41f134836fd9a00e744110c6a812a11b3d95ca70e9485ffe11
high_noise_model/diffusion_pytorch_model-00001-of-00006.safetensors9.99 GBcb58f36df7e604c6e7b0df80a3f6f9b72c77695e581e19985fc3a0e6732ba1e2
high_noise_model/diffusion_pytorch_model-00002-of-00006.safetensors9.94 GB6719620a0feb4553d0306296ba4fad7d6d3b70b666fcbd02ad41fd21df3ab6af
high_noise_model/diffusion_pytorch_model-00003-of-00006.safetensors9.94 GB0eb7864481499e65698ab94ddfad00e1289960b9f1a45aed6530ba6701859513
high_noise_model/diffusion_pytorch_model-00004-of-00006.safetensors9.84 GB8646c9af94dbb2917380dbb6c2ba7fa34332566f2f9f0f508750e377fdad8e0a
high_noise_model/diffusion_pytorch_model-00005-of-00006.safetensors9.84 GB743ca2839d8339eeac1419de9bcfb6f02d4eab4264b01db6d4970047ae9385d0
high_noise_model/diffusion_pytorch_model-00006-of-00006.safetensors7.60 GB78e445e6ca232fb2b8669673b8f7e2f607f84b12e0489429577e8aea624ad7c1
high_noise_model/diffusion_pytorch_model.safetensors.index.json96.8 KBf0d2171c391bb73944c3ff3b279b09c599b20bbba62bb45ac3e56282b840a9a6
low_noise_model/config.json250 B691a47e123c3dd41f134836fd9a00e744110c6a812a11b3d95ca70e9485ffe11
low_noise_model/diffusion_pytorch_model-00001-of-00006.safetensors9.99 GBf2a6df8981742260b3f2cd8b51a276eb0ffa0332c9bbbadc3d625f269096f01c
low_noise_model/diffusion_pytorch_model-00002-of-00006.safetensors9.94 GBea3998b0b394ede1df6c8cb9ea44f1bed0d3d7018bd8113baca9ff74e100b5d9
low_noise_model/diffusion_pytorch_model-00003-of-00006.safetensors9.94 GBe1222162ecdc5a8bb4815f78ae42951cdc3e50a3fe41d8f592462d28f8638681
low_noise_model/diffusion_pytorch_model-00004-of-00006.safetensors9.84 GB9fdd1165fe0c5efd87036b3722e69f1d2004bd27396905a997afb7ddf7f22edf
low_noise_model/diffusion_pytorch_model-00005-of-00006.safetensors9.84 GB04909e9fa1f15de79851230c7f223a0c96fcfd629bdd914b21c9344cec63c78a
low_noise_model/diffusion_pytorch_model-00006-of-00006.safetensors7.60 GB7a481d5adcc53ed3ae8b3222b4c4ee63bac6703dae9ff6c62a7d52e546c88809
low_noise_model/diffusion_pytorch_model.safetensors.index.json96.8 KBf0d2171c391bb73944c3ff3b279b09c599b20bbba62bb45ac3e56282b840a9a6
models_t5_umt5-xxl-enc-bf16.pth11.4 GB7cace0da2b446bbbbc57d031ab6cf163a3d59b366da94e5afe36745b746fd81d
nohup.out939 KB195884e94c146a17a6c7c5b4cdbe8f11936397ed822125aa729004121766ccdf

Use it

$ fw get Wan-AI/Wan2.2-T2V-A14B
# manifest sha256 7b4e1517047a… · 126 GB · 32 files
$ fw verify ./Wan2.2-T2V-A14B Wan-AI/Wan2.2-T2V-A14B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Wan-AI/Wan2.2-T2V-A14B.json --dir ./Wan2.2-T2V-A14B $ python3 fw.py verify ./Wan2.2-T2V-A14B ./Wan-AI__Wan2.2-T2V-A14B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Wan-AI/Wan2.2-T2V-A14B --revision c8c270b13ee05bfa474194ac9fb07a5868a97cea --local-dir ./Wan2.2-T2V-A14B
Packaged for ComfyUI. Most image, video and music models run in ComfyUI . Check the publisher's page for the workflow. Freeweights does not host it.
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Text in
README.md
Text sha256
45aca8eac89096edafa083cd12b4842a696317c318cdfdfd7b1ce4a5840d537f
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: Wan-AI <huggingface.co/Wan-AI>Newsgroups: alt.freeweights.videoSubject: Wan2.2-T2V-A14BDate: 2026-11-14Commit: c8c270bSigned: 2DC28CC7B26A283B ✓
Upstream
Wan-AI/Wan2.2-T2V-A14B
Pinned commit
c8c270b13ee05bfa474194ac9fb07a5868a97cea
Manifest
Wan2.2-T2V-A14B.json · .minisig
Manifest sha256
7b4e1517047a33094ab8c15e1a5039b5c786cfe252ff278cc1d677ca0a3e3d62
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 15:36 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Wan-AI/Wan2.2-T2V-A14B.json $ curl -O https://freeweights.allternit.com/manifests/Wan-AI/Wan2.2-T2V-A14B.json.minisig $ minisign -Vm Wan2.2-T2V-A14B.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Wan-AI/Wan2.2-T2V-A14B
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. Wan2.2-T2V-A14B.json. Provenance. Takedown history: none.
Source
huggingface.co/Wan-AI/Wan2.2-T2V-A14B

Related models

All of alt.freeweights.video →
From: tencent <huggingface.co/tencent>Subject: HunyuanVideo-1.5
From: Lightricks <huggingface.co/Lightricks>Subject: LTX-2.5
From: Wan-AI <huggingface.co/Wan-AI>Subject: Wan2.2-I2V-A14B