---
title: AviadDahan-SepGen-Separation
canonical_url: "https://www.modelscope.cn/models/hf/AviadDahan-SepGen-Separation"
md_url: "https://www.modelscope.cn/models/hf/AviadDahan-SepGen-Separation.md"
repository: hf/AviadDahan-SepGen-Separation
last_updated: 2026-10-09
license: other
model_type:
  - sepgen
base_model:
  - Lightricks/LTX-2.5
base_model_relation: adapter
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 7
stars: 0
tags:
  - audio-video
  - source-separation
  - audio-generation
  - lora
  - ltx-2.5
  - sepgen
---

# AviadDahan-SepGen-Separation

> AviadDahan-SepGen-Separation - hf 在 ModelScope 开源的模型。SepGen separation checkpoint (sep-12k)

hf/AviadDahan-SepGen-Separation 是 ModelScope 魔搭社区上的机器学习模型，采用 other 许可，基于 Lightricks/LTX-2.5 构建。

- **Repository**: hf/AviadDahan-SepGen-Separation
- **License**: other
- **Base model**: Lightricks/LTX-2.5
- **Tags**: audio-video, source-separation, audio-generation, lora, ltx-2.5, sepgen
- **Downloads**: 7
- **Stars**: 0
- **Last updated**: 2026-10-09

Source: https://www.modelscope.cn/models/hf/AviadDahan-SepGen-Separation

---

# SepGen separation checkpoint (`sep-12k`)

**SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model**

**Aviad Dahan**<sup>1</sup>, **Rajaei Khatib**<sup>1</sup>, **Yonatan Bitton**<sup>2</sup>,
**Idan Szpektor**<sup>2</sup>, **Lior Wolf**<sup>1</sup>, **Raja Giryes**<sup>1</sup>

<sup>1</sup>Tel Aviv University, <sup>2</sup>Google

[Paper](https://arxiv.org/abs/2610.11361) · [Project page](https://sepgen.github.io/) · [Code](https://github.com/AviadDahan/SepGen) · Other checkpoint: [gen-3k (generation)](https://huggingface.co/AviadDahan/SepGen-Generation)

SepGen extends LTX-2.5 to emit the video, the audio-mix, and one waveform per captioned source in a
single sampling run. The same weights generate (scene caption and per-source captions → video,
audio-mix and stems) and separate (observed video and audio-mix → stems), selected by the noise
level of the audio-mix.

`sep-12k` is the separation checkpoint: 12,000 training steps in which the audio-mix is always presented clean and the loss is on the two stems. Given a video, its audio-mix and one caption per source, it returns one waveform per source.

## Files

| File | Content |
|---|---|
| `lora_weights.safetensors` | the LoRA adapter (sha256 `fc0987e972c0e92556348ea99b018c9a7c3a95691c4bd46a7d549b1fcd4edd39`) |
| `config.json` | adapter and training summary |
| `train_config.yaml` | the full training config |

The adapter targets the audio stream of the LTX-2.5 22B dev transformer: rank and alpha 128, 480
modules, 327M parameters, bf16, ComfyUI key format (`diffusion_model.`). It is trained with
attention gates (block-diagonal caption routing, the protected audio-mix span, video reading audio
from the audio-mix only, Cross-Stem Attention Guidance) that must also be installed at inference,
so run it with the [SepGen code](https://github.com/AviadDahan/SepGen), not as a plain LoRA.

## Usage

```bash
git clone https://github.com/AviadDahan/SepGen && cd SepGen
bash setup.sh && source activate.sh && bash download_weights.sh
python separate.py --batch-manifest examples/separation_manifest.json --checkpoint sep-12k --out-dir outputs/sep
```

`--checkpoint sep-12k` downloads this repo on first use.

## License

These weights are a Derivative of LTX-2.x and are distributed under the
[LTX-2.x Community License Agreement](https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x),
including its use-based restrictions (Attachment A) and the
[LTX Acceptable Use Policy](https://static.lightricks.com/legal/ltx-acceptable-use-policy.pdf).

## Citation

```bibtex
@article{dahan2026sepgen,
  title   = {SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model},
  author  = {Dahan, Aviad and Khatib, Rajaei and Bitton, Yonatan and Szpektor, Idan and Wolf, Lior and Giryes, Raja},
  journal = {arXiv preprint arXiv:2610.11361},
  year    = {2026}
}
```