---
title: WorldStereo-FP8
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/WorldStereo-FP8"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/WorldStereo-FP8.md"
repository: AI-ModelScope/WorldStereo-FP8
last_updated: 2026-08-02
license: other
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
parameters: 41.9B
tensor_type:
  - BF16
  - F8_E4M3
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 768
stars: 1
tags:
  - ltx-2
  - ltx-video
  - text-to-video
  - audio-video
---

# WorldStereo-FP8

> WorldStereo-FP8 - AI-ModelScope 在 ModelScope 开源的模型。This is a fine-tuned version of ltx-2.3-22b-dev.safetensors trained on custom data.

AI-ModelScope/WorldStereo-FP8 是 ModelScope 魔搭社区上的 41.9B 参数text-to-video-synthesis模型，采用 other 许可。

- **Repository**: AI-ModelScope/WorldStereo-FP8
- **License**: other
- **Tasks**: text-to-video-synthesis
- **Parameters**: 41.9B
- **Tags**: ltx-2, ltx-video, text-to-video, audio-video
- **Downloads**: 768
- **Stars**: 1
- **Last updated**: 2026-08-02

Source: https://www.modelscope.cn/models/AI-ModelScope/WorldStereo-FP8

---

# WorldStereo-FP8

This is a fine-tuned version of [`ltx-2.3-22b-dev.safetensors`](/dev/shm/worldstereo-models/LTX-2.3/ltx-2.3-22b-dev.safetensors) trained on custom data.

## Model Details

- **Base Model:** [`ltx-2.3-22b-dev.safetensors`](/dev/shm/worldstereo-models/LTX-2.3/ltx-2.3-22b-dev.safetensors)
- **Training Type:** LoRA fine-tuning
- **Training Steps:** 1000
- **Learning Rate:** 0.0002
- **Batch Size:** 1

## Sample Outputs

| | | | |
|:---:|:---:|:---:|:---:|


## Usage

This model is designed to be used with the LTX-2 (Lightricks Audio-Video) pipeline.

### 🔌 Using Trained LoRAs in ComfyUI

In order to use the trained LoRA in ComfyUI, follow these steps:

1. Copy your trained LoRA checkpoint (`.safetensors` file) to the `models/loras` folder in your ComfyUI installation.
2. In your ComfyUI workflow:
    - Add the "Load LoRA" node to choose your LoRA file
    - Connect it to the "Load Checkpoint" node to apply the LoRA to the base model

You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the
official [LTX-2 repository](https://github.com/Lightricks/LTX-2).

### Example Prompts




This model inherits the license of the base model ([`ltx-2.3-22b-dev.safetensors`](/dev/shm/worldstereo-models/LTX-2.3/ltx-2.3-22b-dev.safetensors)).

## Acknowledgments

- Base model: [Lightricks](https://huggingface.co/Lightricks/LTX-2)
- Trainer: [LTX-2](https://github.com/Lightricks/LTX-2)