Use with AI
Back to video comparisons

Wan video models

Open video model family · Video

Open model family with text, image, speech-to-video and animation variants.

Wan video models capability illustration
Computational-efficiency table image from the official Wan2.2 GitHub README, retrieved 14 September 2026.

Use it for

Start here when you need an open-model experiment on a suitable GPU.

Choose something else for

WanGP is a runner; Wan is a family of models with different inputs.

Give it

Prompt; Image or audio depending on variant

Get back

Generated video

How it is operated

Application/API or supported runtime; access not rechecked

Availability

Provider capabilities and historical Studio notes are distinguished below. Current account access, credits and runtime readiness were not tested.

How charging works

Compute and model/weight terms; hosted wrappers charge separately.

Where processing happens

Self-hosted if deployed locally, otherwise provider-dependent.

Language support

Exact model version determines support.

Run open video models

★★★★☆ 4/5 for this task

Multiple explicit model variants make it a useful self-hosted route; choose the task-specific variant.

Decision: Start here when you need an open-model experiment on a suitable GPU.

Limits and things to check

WanGP is a runner; Wan is a family of models with different inputs. Budget the full workflow including setup, retries and processing; no universal cost-per-minute claim.

Evidence

Official capability documentation; no comparative production benchmark

Catalogue review: 2026-09-05. The evidence note identifies what was verified. This date does not imply a fresh tool test or verification of every linked source.

Put it to work