THE CURIOUS SIDE OF AI
Wan-AI / VIDEO / AVATAR
Wan 2.1 / small video
A compact text-to-video model for short creative scenes and effects experiments.
Source reviewed 2026-10-24 · AiBrainWorX editorial summary
- Creator
- Wan-AI
- Parameters
- 1.3B
- Context
- Video duration and resolution are runtime-specific
- License
- Apache-2.0
01 / CAPABILITIES
What it is built for
- Local video-generation workflow
- Dedicated video runtime required
Inputs: Text → video
Video frames and audio samples are not a text context window.
02 / ON YOUR MACHINE
Consumer GPU candidate; publisher lists 8.19 GB VRAM
The publisher recommends 480p and reports 8.19 GB VRAM. Their timing is on an RTX 4090; no RTX 3060 timing has been measured here. Text-to-video alone does not establish a personal avatar identity or lip sync.
External video runtime; not installed or wired to Chat generation
Runtime and training workflow
Wan official runtime · Compatible ComfyUI workflow
External video-specific fine-tuning. Training suitability requires exact checkpoint format and prepared data; a catalog entry is not a completed training test.
03 / WHAT IS VERIFIED
Evidence, with context
Source reviewed only. No local rendering or avatar quality test performed.
We have not added a benchmark number without documenting its test conditions. A model-card capability is not a measured speed or quality guarantee on your hardware.
04 / OWNERSHIP & USE
Apache-2.0
Review exact checkpoint, dependencies and input-media rights. No weights or runtime are bundled.
AiBrainWorX authors this profile and the launcher. Wan-AI remains the model’s creator. Models are not rebranded as our own weights.
05 / GO DEEPER
Original sources & model files
This page is our concise summary, not a mirror of the full upstream card. Review the original documentation and exact artifact before downloading.
Reviewed revision: 37ec512624d6 · Specifications may change after the review date.