This model requires you to accept the Apache 2.0 license terms before download.
Description
Dual-expert image-to-video diffusion, two 14B denoisers with boundary switching, 480P and 720P clips.
Tags
At a glance
| Kind | video generation model |
|---|---|
| Precision | float32 |
| Container size | 118 GiB |
| Weights inside | 118 GiB |
| Components | 4 |
| Licence | Apache 2.0 |
| Origin | Wan-AI/Wan2.2-I2V-A14B-Diffusers @ 596658fd9ca6 |
What is inside the container
A .nbx container packs every part of Wan2.2-I2V-A14B-Diffusers — 4 components with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| transformer | 40 | 40 | 53.2 GiB |
| transformer_2 | 40 | 40 | 53.2 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 Wan2.2-I2V-A14B-Diffusers take 118 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 118 GiB (126,699,160,577 bytes).
$ sha256sum Wan2.2-I2V-A14B-Diffusers.nbx
1b97aac7d57bb597faabaa769b7f952291d34cc6117c9200909b0009d76f5be0
Questions
What is Wan2.2-I2V-A14B-Diffusers?
A video generation model by Wan-AI, distributed as a float32 .nbx container and licensed Apache 2.0.
How big is the download?
118 GiB, of which 118 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/Wan2.2-I2V-A14B-Diffusers, then neurobrix serve --model Wan2.2-I2V-A14B-Diffusers.
CLI Usage
$ neurobrix import Wan-AI/Wan2.2-I2V-A14B-Diffusers
$ neurobrix serve --model Wan2.2-I2V-A14B-Diffusers
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop