This model requires you to accept the Apache 2.0 license terms before download.
Description
All-in-one video creation and editing (VACE), 1.3B parameters. Text-to-video generation is validated and reproducible: at 480x832, 9 frames, guidance 5.0 it renders bit-identically to its 2026-06-28 validation on both engines (re-checked 2026-09-03). Declared limitation at this release: generation conditioned on a REFERENCE IMAGE is not supported - that path stops on a channel-size mismatch and is tracked as a named fix. Use the prompt-only mode; the sibling Wan2.1-T2V-1.3B covers plain text-to-video as well.
Tags
At a glance
| Kind | video generation model |
|---|---|
| Precision | float32 |
| Container size | 18.2 GiB |
| Weights inside | 18.2 GiB |
| Components | 3 |
| Licence | Apache 2.0 |
| Origin | Wan-AI/Wan2.1-VACE-1.3B-diffusers @ ec4d2cb062b5 |
What is inside the container
A .nbx container packs every part of Wan2.1-VACE-1.3B-diffusers — 3 components with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| transformer | 30 | 30 | 6.7 GiB |
| vae | 11 | — | 484 MiB |
| text_encoder | 24 | 24 | 10.6 GiB |
Default settings
The values the container ships with. They apply when you do not pass your own.
- Frames
- 81
- Frames per second
- 16
- Inference steps
- 50
- Guidance scale
- 5
Memory needed
The weights of Wan2.1-VACE-1.3B-diffusers take 18.2 GiB in float32. That is the floor for the memory the runtime has to place, spread over the devices it finds; activations come on top and grow with the size and length you ask for. A measured peak per device class is not published for this model yet.
Verify what you downloaded
Every download carries its SHA-256, and the file endpoint sends it in the X-NBX-SHA256 header. The container is 18.2 GiB (19,536,772,543 bytes).
$ sha256sum Wan2.1-VACE-1.3B-diffusers.nbx
23fe27df97b40c142d5af4b6eb1a0433ebc76e868a341c6645983463b3de99c4
Questions
What is Wan2.1-VACE-1.3B-diffusers?
A video generation model by Wan-AI, distributed as a float32 .nbx container and licensed Apache 2.0.
How big is the download?
18.2 GiB, of which 18.2 GiB are weights.
How do I run it?
Install the runtime from the download page, then use the commands under “CLI Usage” below: neurobrix import Wan-AI/Wan2.1-VACE-1.3B-diffusers, then neurobrix serve --model Wan2.1-VACE-1.3B-diffusers.
CLI Usage
$ neurobrix import Wan-AI/Wan2.1-VACE-1.3B-diffusers
$ neurobrix serve --model Wan2.1-VACE-1.3B-diffusers
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop