This model requires you to accept the NVIDIA Open Model license terms before download.
Description
Efficient 720p text-to-video generation, 2B parameters, linear-attention diffusion transformer.
Tags
At a glance
| Kind | video generation model |
|---|---|
| Precision | float32 |
| Container size | 17.1 GiB |
| Weights inside | 17.1 GiB |
| Components | 3 |
| Licence | NVIDIA Open Model |
| Origin | Efficient-Large-Model/SANA-Video_2B_720p_diffusers @ 82de0b2398cd |
What is inside the container
A .nbx container packs every part of SANA-Video_2B_720p_diffusers — 3 components with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| transformer | 20 | 20 | 7.7 GiB |
| vae | 5 | — | 4.6 GiB |
| text_encoder | 26 | — | 4.9 GiB |
Default settings
The values the container ships with. They apply when you do not pass your own.
- Height (px)
- 704
- Width (px)
- 1280
- Frames
- 81
- Frames per second
- 16
- Inference steps
- 50
- Guidance scale
- 6
Memory needed
The weights of SANA-Video_2B_720p_diffusers take 17.1 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 17.1 GiB (18,356,300,200 bytes).
$ sha256sum SANA-Video_2B_720p_diffusers.nbx
8ff9cdc4612baad67a03702fec0fe45291d29c28ce2470736c2cc8430b0f653b
Questions
What is SANA-Video_2B_720p_diffusers?
A video generation model by Efficient-Large-Model, distributed as a float32 .nbx container and licensed NVIDIA Open Model.
How big is the download?
17.1 GiB, of which 17.1 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 Efficient-Large-Model/SANA-Video_2B_720p_diffusers, then neurobrix serve --model SANA-Video_2B_720p_diffusers.
CLI Usage
$ neurobrix import Efficient-Large-Model/SANA-Video_2B_720p_diffusers
$ neurobrix serve --model SANA-Video_2B_720p_diffusers
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop