---
title: LTX-2-Repackage
canonical_url: "https://www.modelscope.cn/models/DiffSynth-Studio/LTX-2-Repackage"
md_url: "https://www.modelscope.cn/models/DiffSynth-Studio/LTX-2-Repackage.md"
repository: DiffSynth-Studio/LTX-2-Repackage
last_updated: 2026-03-06
license: "Apache License 2.0"
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
base_model:
  - Lightricks/LTX-2
base_model_relation: repackage
parameters: 40.5B
tensor_type:
  - BF16
  - F32
library_name:
  - pytorch
  - safetensors
frameworks:
  - Pytorch
downloads: 13565
stars: 1
---

# LTX-2-Repackage

> LTX-2-Repackage - DiffSynth-Studio 在 ModelScope 开源的模型。Repackaged model of LTX-2 Why we repackage? All models in offical repo of LTX-2 are stored in a single file. For better usage in DiffSynth-Studio, we have repackeged the official checkpoints in this repo…

DiffSynth-Studio/LTX-2-Repackage 是 ModelScope 魔搭社区上的 40.5B 参数text-to-video-synthesis模型，采用 Apache License 2.0 许可，基于 Lightricks/LTX-2 构建。

- **Repository**: DiffSynth-Studio/LTX-2-Repackage
- **License**: Apache License 2.0
- **Tasks**: text-to-video-synthesis
- **Parameters**: 40.5B
- **Base model**: Lightricks/LTX-2
- **Downloads**: 13565
- **Stars**: 1
- **Last updated**: 2026-03-06

Source: https://www.modelscope.cn/models/DiffSynth-Studio/LTX-2-Repackage

---

# Repackaged model of LTX-2
## Why we repackage?
All models in offical repo of LTX-2 are stored in a single file. For better usage in DiffSynth-Studio, we have repackeged the official checkpoints in this repo to support separate loading of different submodules and avoid redundant memory usage when users only want to use part of the model.

|Model Name|File|
|-|-|
|dit|transformer.safetensors|
|distilled dit|transformer_distilled.safetensors|
|video_vae_encoder|video_vae_encoder.safetensors|
|video_vae_decoder|video_vae_decoder.safetensors|
|audio_vae_encoder|audio_vae_encoder.safetensors|
|audio_vae_decoder|audio_vae_decoder.safetensors|
|audio_vocoder|audio_vocoder.safetensors|
|text_encoder_post_modules|text_encoder_post_modules.safetensors|

## Example usage in DiffSynth-Studio

Install DiffSynth-Studio：

```
git clone https://github.com/modelscope/DiffSynth-Studio.git  
cd DiffSynth-Studio
pip install -e .
```

Model Inference:

```python
import torch
from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2

vram_config = {
    "offload_dtype": torch.bfloat16,
    "offload_device": "cpu",
    "onload_dtype": torch.bfloat16,
    "onload_device": "cuda",
    "preparing_dtype": torch.bfloat16,
    "preparing_device": "cuda",
    "computation_dtype": torch.bfloat16,
    "computation_device": "cuda",
}
"""
Offical model repo: https://www.modelscope.cn/models/Lightricks/LTX-2
Repackaged model repo: https://www.modelscope.cn/models/DiffSynth-Studio/LTX-2-Repackage
For base models of LTX-2, offical checkpoint (with model config ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors"))
and repackaged checkpoints (with model config ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="*.safetensors")) are both supported.
We have repackeged the official checkpoints in DiffSynth-Studio/LTX-2-Repackage repo to support separate loading of different submodules,
and avoid redundant memory usage when users only want to use part of the model.
"""
# use the repackaged modelconfig from "DiffSynth-Studio/LTX-2-Repackage" to avoid redundant model loading
pipe = LTX2AudioVideoPipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors", **vram_config),
        ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors", **vram_config),
    ],
    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
)
# use the following modelconfig if you want to initialize model from offical checkpoints from "Lightricks/LTX-2"
# pipe = LTX2AudioVideoPipeline.from_pretrained(
#     torch_dtype=torch.bfloat16,
#     device="cuda",
#     model_configs=[
#         ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
#         ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors", **vram_config),
#     ],
#     tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
# )
prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
height, width, num_frames = 512, 768, 121
video, audio = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    seed=43,
    height=height,
    width=width,
    num_frames=num_frames,
    tiled=True,
)
write_video_audio_ltx2(
    video=video,
    audio=audio,
    output_path='ltx2_onestage.mp4',
    fps=24,
    audio_sample_rate=24000,
)
```