---
license: apache-2.0
language:
- en
base_model:
- Wan-AI/Wan2.1-I2V-14B-720P
tags:
- lora
- wan
- comfyui
- motion
pipeline_tag: image-to-video
---
# Push-in camera — A Motion LoRA for Wan 2.1 (14B - 720p)

<video src="https://lovis.io/videofullv2.mp4" controls="controls" style="max-width: 100%;"></video>

This LoRA was trained on 100 clips to introduce realistic, high-quality push-in drone camera motion into your generations. While the [Wan 2.1 I2V 720p](https://huggingface.co/wan-fusion/wan-2.1-i2v-720p) model produces great image quality, it can sometimes lack meaningful movement. `Push-in camera` enhances your creations by delivering natural camera dynamics across various styles and scenes.

This final version is the result of over 40 iterations of tweaking and refining to achieve a truly cinematic motion.

## 🚀 How to Use

To use this LoRA, you need to use the trigger word `Push-in camera` in your prompt.

**Example prompt:**
`Push-in camera, Instantly rocketing towards the heart of the lavender field, the vibrant purple blooms blurring into a hypnotic, swirling vortex of color as the rows of lavender, each individual flower a tiny point of light, rush towards the viewer, the distant cypress trees transforming into sharp, dark silhouettes against a breathtaking sunset sky, the soft golden light illuminating every minute detail of the scene, until the camera slams into the heart of the field, revealing the intricate texture of the blossoms, the delicate variations in purple hues, and the subtle golden undertones of the setting sun, in breathtaking, hyper-real clarity.`

### 🧩 ComfyUI Workflow

A complete [ComfyUI](https://github.com/comfyanonymous/ComfyUI) workflow is available to help you get started instantly. This makes the LoRA directly usable without any complex setup.

You can download the workflow file here: [workflow-pushin-v2-comfyui.json](workflow-pushin-v2-comfyui.json)

![ComfyUI Workflow](workflow-pushin-v2-comfyui.png)

## 🎬 Examples

Here are some examples of the push-in effect generated with this LoRA.

| Input Image | Generated Video |
| :---: | :---: |
| ![Input Image 1](image-video/01.png) | <video src="https://lovis.io/01.mp4" controls="controls" style="max-width: 100%;"></video> |
| ![Input Image 2](image-video/02.jpg) | <video src="https://lovis.io/02.mp4" controls="controls" style="max-width: 100%;"></video> |


## 🛠️ Model Details

- **Base Model:** [Wan 2.1 I2V 720p](https://huggingface.co/wan-fusion/wan-2.1-i2v-720p)
- **Trigger Word:** `Push-in camera`
- **Training:** Trained on 100 carefully curated clips.
- **Compatibility:** Ideal for cinematic sequences, storytelling shots, and dynamic framing. It adapts beautifully across all styles.

## Feedback

This LoRA is also available on Civitai. I'm curious to hear your feedback!

Feel free to open an issue or reach out with any questions.