Kimodo

Kimodo

Generates motions from text prompts with NVIDIA's Kimodo models, in a page you can open in a browser or build yourself with Docker. For animators and researchers.

Made by nvidia on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Kimodo is an NVIDIA Space that generates motions from a text prompt. It names two models, nvidia/Kimodo-SOMA-RP-v1 and nvidia/Kimodo-G1-RP-v1, and runs as a Docker app on a GPU at Hugging Face. You can use it in a browser with nothing to install.

Who it suits: It suits animators, game developers and researchers who want to turn a written description into a motion and see what the models produce.

Industry | Who uses it | How they use it | Example
Animation | Animators | Try a written description as a starting point for a motion | Type a short action and look at the result
Game development | Game developers | Test how text prompts turn into motion | Compare results from a few different prompts
AI research | Researchers | Try the two Kimodo models in a hosted demo | Open the Space and run a prompt

If you have no use for generated motion, you can skip it.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Windows, macOS or Linux with Docker, from a local build of the Space's files

Use case | Who | What they get back
Try a motion prompt | Animators | A generated motion from a text description
Compare prompts | Developers | Different motions from different wording
Run it yourself | Researchers | A local Docker copy of the app on port 7860

How to set it up:

• A web browser, which is all the online page needs
• Docker and Python with pip, for a local copy
• The Python packages listed in requirements.txt, which the Dockerfile handles

1. Open the Space's page on Hugging Face to use it online. Nothing needs installing.
2. For a local copy, install the Hugging Face hub package and download the Space's files.
3. Move into the downloaded folder.
4. Build the Docker image, then run it with port 7860 published.

pip install -U huggingface_hub
hf download nvidia/Kimodo --repo-type space --local-dir Kimodo
cd Kimodo
docker build -t kimodo .
docker run -it -p 7860:7860 kimodo

How to use it: Open the page, or port 7860 on your own machine once the container runs, and write a prompt that describes the motion you want. The app then generates a motion from that text.

Example: Type a short sentence that describes an action. The app turns the sentence into a motion that you can look at in the page.

For newcomers and experts: Open the Space page and try one short prompt first. Nothing needs installing, and the result shows what the models can do.

The repository is small, with a Dockerfile, start.sh, requirements.txt and a LICENSE file, and the online copy uses l40sx1 hardware at Hugging Face. The two models named are nvidia/Kimodo-SOMA-RP-v1 and nvidia/Kimodo-G1-RP-v1. The README says little else, so the details of the output format are not documented.

You write a text prompt
The app passes it to a Kimodo model
The model generates a motion
The page shows the motion

Good to know: The source gives no limits on prompt length or output format.

• License: Apache 2.0
• Cost to run: none named, though the online copy runs on l40sx1 hardware at Hugging Face
• Data it reaches: the text prompts you enter and the two nvidia/Kimodo models

On Hugging Face, 13 November 2026

• Likes: 340
• Built with: docker
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/nvidia/Kimodo
• Files: https://huggingface.co/spaces/nvidia/Kimodo/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.