---
license: openrail++
base_model: stabilityai/stable-diffusion-2-1-base
tags:
  - controlnet
  - stable-diffusion
  - diffusion
  - radio-map
  - wireless-communications
  - pytorch-lightning
  - research
  - "arxiv:2608.09357"
---

# ControlRadio

## Prompt-Driven Controllable Diffusion for Cross-Modal Radio Map Generation

**Kangjun Liu · Xiying Pan · Shuhang Zhang · Xiang Xiang · Ke Chen · Yaowei Wang**

[Paper](https://arxiv.org/abs/2608.09357) · [HTML](https://arxiv.org/html/2608.09357v1) · [PDF](https://arxiv.org/pdf/2608.09357) · [Code](https://github.com/AkonLau/ControlRadio) · [RadioMapSeer](https://radiomapseer.github.io/)

ControlRadio is a prompt-driven controllable diffusion framework for cross-modal radio map generation. It combines natural-language descriptions with environmental layouts, including building morphology, transmitter locations, and optional dynamic-object cues, to synthesize structurally consistent and propagation-plausible radio maps.

> This repository hosts the pretrained weights. Training, evaluation, and inference code is maintained in the [ControlRadio GitHub repository](https://github.com/AkonLau/ControlRadio).

<p align="center">
  <img src="assets/controlradio_framework.png" alt="ControlRadio framework" width="100%">
</p>

## Model Description

ControlRadio builds on [Stable Diffusion 2.1 Base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base) and introduces:

- prompt-guided semantic conditioning with a frozen OpenCLIP text encoder;
- a Layout-Aware ControlNet for building, transmitter, and optional car conditions;
- a Noise Controller for controlling the latent prior used at inference time; and
- decoupled two-stage fine-tuning of a radio-domain VAE followed by the U-Net and ControlNet.

The released files are PyTorch Lightning checkpoints used by the research code. They are not standalone Diffusers or Transformers checkpoints and cannot be loaded directly with `from_pretrained()`.

## Released Checkpoints

| Model | Setting | `--carsInput` | Checkpoint | Size |
|---|---|---:|---|---:|
| ControlRadio-SRM | Static radio maps without cars | `no` | [`epoch=99-step=337499.ckpt`](experiments/prompt_v6/RadioMapSeer_RadioDiff-Seer-no-carsInput/control_sd21_3ch_1e-05_3_100_sd_tune_seed1230/lightning_logs/version_0/checkpoints/epoch=99-step=337499.ckpt) | 13.7 GB |
| ControlRadio-DRM | Dynamic radio maps with cars | `yes` | [`epoch=99-step=506249.ckpt`](experiments/prompt_v6/RadioMapSeer_RadioDiff-Seer-carsInput/control_sd21_3ch_1e-05_3_100_sd_tune_seed1230/lightning_logs/version_0/checkpoints/epoch=99-step=506249.ckpt) | 13.7 GB |

Each experiment directory also contains the corresponding `hparams.yaml`. Keep the downloaded directory structure unchanged because the evaluation and inference scripts construct checkpoint paths from the command-line configuration.

## Installation and Download

Clone the code repository and create the reference environment:

```bash
git clone https://github.com/AkonLau/ControlRadio.git
cd ControlRadio
conda env create -f environment.yaml
conda activate control
```

Install a Hugging Face Hub CLI version compatible with the reference Transformers environment, then download both checkpoints into the project root:

```bash
pip install "huggingface_hub>=0.30,<1.0"
hf download akon1995/ControlRadio --include "experiments/**" --local-dir .
```

The resulting layout is:

```text
ControlRadio/
`-- experiments/
    `-- prompt_v6/
        |-- RadioMapSeer_RadioDiff-Seer-no-carsInput/
        |   `-- control_sd21_3ch_1e-05_3_100_sd_tune_seed1230/
        |       `-- lightning_logs/version_0/checkpoints/
        |           `-- epoch=99-step=337499.ckpt
        `-- RadioMapSeer_RadioDiff-Seer-carsInput/
            `-- control_sd21_3ch_1e-05_3_100_sd_tune_seed1230/
                `-- lightning_logs/version_0/checkpoints/
                    `-- epoch=99-step=506249.ckpt
```

## Evaluation and Inference

For both checkpoints, use the following checkpoint-selection arguments:

```text
--simulation Seer
--prompt_type v6
--batch_size 3
--learning_rate 1e-5
--max_epochs 100
--sd_locked False
--seed 1230
```

Select ControlRadio-SRM with `--carsInput no` or ControlRadio-DRM with `--carsInput yes`. Use `--test_simulation DPM`, `IRT2`, or `IRT4` to select the evaluation target. The paper uses Noise Controller settings `--means -0.1 --vars 0.001` selected on the validation set.

See the [GitHub evaluation and inference instructions](https://github.com/AkonLau/ControlRadio#evaluation-and-inference) for complete commands and data preparation.

## Results

<p align="center">
  <img src="assets/controlradio_results.png" alt="Qualitative ControlRadio results" width="90%">
</p>

Results reported in the paper on the RadioMapSeer benchmark are:

| Scenario | RMSE ↓ | NMSE ↓ | PSNR ↑ | SSIM ↑ |
|---|---:|---:|---:|---:|
| SRM (DPM without cars) | **0.0166** | **0.0024** | **35.86** | **0.9787** |
| DRM (DPM with cars) | **0.0180** | **0.0028** | **35.29** | **0.9759** |
| IRT4 (without cars) | **0.0210** | **0.0040** | **33.46** | **0.9688** |

## Training Data

The models were trained and evaluated with [RadioMapSeer](https://radiomapseer.github.io/). The code follows the paper's map-level split: maps 0–499 for training, 500–599 for validation, and 600–700 for testing. Refer to the dataset provider for its terms and documentation.

## Intended Use and Limitations

ControlRadio is released for research on prompt- and layout-conditioned radio-map generation. The reported results compare generated maps with WinProp-derived references on simulated, previously unseen layouts.

- The released checkpoints have not been validated as replacements for site-specific electromagnetic solvers or field measurements.
- Performance should not be interpreted as sim-to-real validation or strict electromagnetic equivalence.
- Predictions depend on data preprocessing, prompt construction, coordinate conventions, and inference settings matching the released code.
- Users are responsible for validating generated maps before applying them to safety-critical or operational wireless-network decisions.

## License

The model weights are released under the `openrail++` license metadata, consistent with the [Stable Diffusion 2.1 Base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base) foundation model. The ControlRadio source code is separately released under the [MIT License](https://github.com/AkonLau/ControlRadio/blob/main/LICENSE).

## Citation

```bibtex
@article{liu2026controlradio,
  title   = {ControlRadio: Prompt-Driven Controllable Diffusion for Cross-Modal Radio Map Generation},
  author  = {Liu, Kangjun and Pan, Xiying and Zhang, Shuhang and Xiang, Xiang and Chen, Ke and Wang, Yaowei},
  journal = {arXiv preprint arXiv:2608.09357},
  year    = {2026}
}
```

## Acknowledgements

This work builds upon [ControlNet](https://github.com/lllyasviel/ControlNet), [Stable Diffusion](https://github.com/CompVis/stable-diffusion), [OpenCLIP](https://github.com/mlfoundations/open_clip), and [RadioMapSeer](https://radiomapseer.github.io/).