---
license: apache-2.0
language:
- en
base_model:
- Wan-AI/Wan2.2-TI2V-5B
pipeline_tag: image-to-video
tags:
- robotics
- video-generation
- world-model
- multiview
- robot-manipulation
- simulation
library_name: diffusers
---
# PrimeSim

An action-conditioned, multiview world model that runs as a robot simulator. Given
the first frame of each camera view, a prompt and an action trajectory, it generates
what happens next.

- **Paper:** [arXiv 2611.04870](https://arxiv.org/abs/2611.04870)
- **Project page:** [primebottech.github.io/PrimeSim-website](https://primebottech.github.io/PrimeSim-website/)
- **Code:** [github.com/PrimebotTech/PrimeSim](https://github.com/PrimebotTech/PrimeSim) -- inference and training code

Trained on 30,110 hours of cross-embodiment data spanning 22 platforms. In simulation
it leads four of five WorldSimProbe suites and posts the best overall EWMBench score.

## Files

| file | use |
| --- | --- |
| `primesim_base.safetensors` | the midtrained model -- start here to fine-tune |
| `primesim_posttrain_g2.safetensors` | stage 4, causal few-step model -- use for inference |

Run `primesim_posttrain_g2` on the demos in the
[repository](https://github.com/PrimebotTech/PrimeSim) to see what posttraining adds.

## Requirements

**These weights are not self-contained.** The text encoder, VAE and tokenizer come
from [Wan-AI/Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B):

```bash
hf download Wan-AI/Wan2.2-TI2V-5B \
  --include "models_t5_umt5-xxl-enc-bf16.pth" "Wan2.2_VAE.pth" "google/umt5-xxl/*" \
  --local-dir checkpoints
```

Point `config/model/primesim.yaml` at the three resulting paths.

## Inference

Three camera views are generated together at 192x256, running above 10 FPS. An A100
or H100 (80 GB) is recommended: the 5B transformer and the 11 GB text encoder are
resident at the same time, which does not fit on a 24 GB card.

## License

Apache 2.0. **The training corpus is not distributed** and is not covered by this
licence -- the weights are released, the data is not.