---
title: LTX-2-19b-LoRA-Camera-Control-Dolly-Out
canonical_url: "https://www.modelscope.cn/models/Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Out"
md_url: "https://www.modelscope.cn/models/Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Out.md"
repository: Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Out
last_updated: 2026-01-06
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
base_model:
  - Lightricks/LTX-2
base_model_relation: adapter
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 629
stars: 0
tags:
  - lora
  - video
  - camera-motion
  - dolly-out
  - text-to-video
---

# LTX-2-19b-LoRA-Camera-Control-Dolly-Out

> LTX-2-19b-LoRA-Camera-Control-Dolly-Out - Lightricks 在 ModelScope 开源的模型。LTX-2 19B LoRA - Camera Control (Dolly Out)

Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Out 是 ModelScope 魔搭社区上的text-to-video-synthesis模型，基于 Lightricks/LTX-2 构建。

- **Repository**: Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Out
- **Tasks**: text-to-video-synthesis
- **Base model**: Lightricks/LTX-2
- **Tags**: lora, video, camera-motion, dolly-out, text-to-video
- **Downloads**: 629
- **Stars**: 0
- **Last updated**: 2026-01-06

Source: https://www.modelscope.cn/models/Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Out

---

# LTX-2 19B LoRA - Camera Control (Dolly Out)

This is a **camera-motion control LoRA** trained to bias generations toward a **dolly-out camera move** (camera pulls backward away from the subject, often decreasing subject scale and revealing more of the environment) on top of an **LTX-2 19B** base video model.


## Model Details

- **Developed by** Lightricks
- **Base Model**: LTX-2 19B
- **Training Type**: LoRA finetune for camera motion (dolly out)


## Recommended Prompting

- To get the best results with Motion Camera LoRAs, you should describe the "destination" of the movement and the hidden parts of the scene so the AI knows exactly what to reveal as the frame shifts. By detailing what exists at the end of the shot—such as the far side of a room, the full set around the subject, or the space behind the camera—you provide the model with a visual "map" that helps achieve your desired results.

## License

See the base model license: [LTX-2 LICENSE](https://huggingface.co/Lightricks/LTX-2/blob/main/LICENSE).