---
license: cc-by-4.0
tags:
- audio-visual-learning
- acoustic
- audio
- computer-vision
- pytorch
library_name: pytorch
---

# FLAC

Official model weights for **FLAC**, from the paper "Few-shot Acoustic Synthesis with Multimodal Flow Matching" by Amandine Brunetto (CVPR 2026). 

FLAC is a model for generating room impulse responses in novel scenes in a one-shot setting, relying only on a single RIR example and a depth image. 

This repository contains the pretrained weights. To run FLAC, please use the official [codebase](https://github.com/AmandineBtto/FLAC).

---

# Available checkpoints

| file | description |
|-----|-------------|
| FLAC.ckpt | main trained model on the AR dataset |
| FLAC_EMA.ckpt | EMA weights for finetuning FLAC on the HAA dataset |
| FLAC_HAA.ckpt | fine-tuned FLAC model on the HAA dataset |
| VAE.safetensors | VAE model for training FLAC |
| VAE.ckpt | VAE model for VAE evaluation |

---

# Download

Weights can be downloaded with:

```bash
huggingface-cli download AmandineBtto/FLAC --local-dir weights/FLAC
```