Shotcraft
Video generation

Wan 2.2 T2V-A14B

Generates video from a text prompt using a mixture-of-experts diffusion transformer with 27B total and 14B active parameters, split into a high-noise expert for layout and a low-noise expert for detail.

A video generation model by Alibaba Tongyi Lab (Wan) · read 2026-08-14 · sourcing high

Resolution
720P
Weights
Downloadable
API
Yes
Commercial use
Vendor states commercial use is permitted

Supports 480P and 720P output and accepts English or Chinese prompts. Weights, inference code and diffusers integration are all published.

Commercial use — Vendor states commercial use is permitted

Apache-2.0. The repository states: 'The models in this repository are licensed under the Apache 2.0 License.

The licence notes recorded during research were read for a commercial-use position and did not state one. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Alibaba Tongyi Lab (Wan)'s own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in
text
What it makes
video
Maximum duration
not established
Maximum resolution
720P
Aspect ratios
not established
Controls
text prompt, negative prompt, resolution selection, seed, prompt extension via LLM, multi-GPU FSDP/DeepSpeed Ulysses inference, LoRA fine-tuning via community tooling
Weights
Downloadable
API
Yes
Pricing
Free open weights (Apache-2.0) for self-hosting. Official README states at least 80GB VRAM is required for single-GPU A14B inference, so this variant realistically needs an A100/H100-class GPU or multi-GPU sharding; community FP8/GGUF quantizations reduce this but are not vendor-supported. Also offered as a paid hosted API through Alibaba Cloud Model Studio (Bailian), and on third-party hosts such as Replicate and fal.
Released or updated
2025-07-28
Prompt limit
512 tokens (UMT5-XXL text encoder)Vendor figure, checked 2026-08-16Collected from the vendor's own documentation on 16 August 2026. Vendors change these between model versions without announcing it, so check the vendor's current API reference before you rely on it. Check the vendor's documentation

Maximum duration and supported aspect ratios are not established here. That means no page we could retrieve stated them, not that the model lacks them.

Strengths

  • Truly permissive Apache-2.0 license with no revenue or user thresholds
  • Strong motion quality and prompt adherence for an open model
  • Large ecosystem of LoRAs, ComfyUI workflows and community quantizations
  • Bilingual English/Chinese prompting
  • Cinematic aesthetic controls trained on labelled lighting/composition data

Weaknesses

  • 80GB VRAM for official single-GPU inference puts it out of reach of consumer hardware without quantization
  • Official docs omit frame count and fps for this variant
  • Capped at 720P native; no 1080P/4K path
  • No native audio generation

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

MCP servers that front Alibaba Tongyi Lab (Wan)

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Wan 2.1 T2V (1.3B and 14B)

The first widely adopted Apache-2.0 video generation family. T2V-1.3B generates 480P and fits in about 8.19GB of VRAM; T2V-14B handles 480P and 720P.

Video generation

Wan 2.2 I2V-A14B

Animates a still image into video, optionally guided by a text prompt, using the same 27B/14B-active mixture-of-experts architecture as the text-to-vi

Video generation

Wan 2.2 S2V-14B

Audio-driven video generation: takes a reference image plus an audio track and produces a speaking or performing subject synchronized to that audio. O

Video generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.