---
license: apache-2.0
library_name: diffusers
pipeline_tag: text-to-video
tags:
- text-to-video
- text to video
---
# FlowingFrames

FlowingFrames is a text-to-video model that leverages past frames for conditioning, enabling the generation of infinite-length videos. It supports flexible resolutions, various configurations for frames and inference steps, and prompt interpolation for creating smooth scene changes.

## Installation

### Clone the Repository

```bash
git clone https://github.com/motexture/FlowingFrames.git
cd FlowingFrames
python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`
pip install -r requirements.txt
python run.py
```

Visit the provided URL in your browser to interact with the interface and start generating videos.

## Samples

<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64a86f7d03835e13f95c3687/yGIhFrRtqwUH2QU0Xroul.mp4"></video>
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64a86f7d03835e13f95c3687/ZCvSsuL-ZenWrUi24HQAh.mp4"></video>
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64a86f7d03835e13f95c3687/RURlytx4ooNMFY3L32AB1.mp4"></video>
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64a86f7d03835e13f95c3687/3nFXX1UKAx7NSTqA4IoJB.mp4"></video>
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64a86f7d03835e13f95c3687/QA11CGZ3WKucBcyEh5ULx.mp4"></video>

## Extras

You can use this GPT to generate highly detailed image prompts -> [Image Prompter](https://chatgpt.com/g/g-rRGhg9gA6-image-prompter)

## Additional Info

Spatial layers are from Stable Diffusion XL 1.0