【☰】Table of Contents 👆

DepthFlow

_{👆 Out of the many Explorers, you can be among the Shining stars who support us! ⭐️}

[DepthFlow]: Image to → 2.5D Parallax Effect Video. A Professional [Depthy] Alternative.

👇 Right click and loop me!

DepthFlow.2023.12.19.mp4

^{Note: Yes, the only input to DepthFlow was the Original Image}

🎩 Click to see the Original Image

Source: Wallhaven. All images remain property of their original owners. ⚖️

🪄 Click to see the Estimated Depth map

The Depth Map was estimated with ZoeDepth 🚀

🔥 Description

💡 Base idea:

1. Given an image and its depth map, have a shader to generate a parallax effect
2. Estimate Depth Maps with Neural Networks for generic images
3. Varying the projections over time generates a 2.5D video

As simple as that, we achieve a similar effect as Depthy

📦 Installation

🔴🟡🟢

Download and install our Monorepo with all the code and projects first

_{Note: You cannot run this project in dev mode without the Framework!}

• DepthFlow directly uses ShaderFlow. Check it out! 🚀

Running the code

After running the brakeit script on the Monorepo and inside the Virtual Environment,

• Run the command: broken depthflow

A real time window should pop up.

Selecting the input image

• Run broken depthflow parallax --help for parallax options

• You can also drag and drop an Image File or URL From your Browser

Rendering Options

• Run broken depthflow --help for options and rendering

Full Examples

• broken depthflow (--render | -r)
• broken depthflow -r -w 1280 -h 720 -f 30
• broken depthflow -r -o ./video_name --format mkv
• broken depthflow parallax --image (url | path) main --render -s 2
• broken depthflow -r -t 2 --open
• broken depthflow parallax -i (image) -d (depth) main

Note: A high SSAA -s 1.5 is recommended for antialiasing due the Steep Parallax

🚀 Using your GPU

By default, Pytorch will be installed with CPU support.

If you want to Speed Up the Depth Estimation, you can add Pytorch with GPU support:

NVIDIA^N1 (CUDA):

• Have the NVIDIA Drivers installed - Windows might already have installed them
• Run the command: broken depthflow poe cuda

_{*N1: Check GPU compatibility (<= GTX 800 series is not supported). Preferably install CUDA from your package manager.}

AMD^R1 (ROCm):

• Run the command: broken depthflow poe rocm

_{*R1: Check GPU compatibility (<= RX 500 series is not supported). Preferably install ROCm from your package manager}

CPU / macOS (Default):

• Run the command: broken depthflow poe cpu

⚖️ License

See BrokenSource Repository for the License of the Code Assets, Projects and User Generated Content.