Logo Swap

Introduction

LogoSwap lets you remove and replace logos without any manual tracking. It does so by loading an AI model (.swp / SwapFile) and using the trained information to detect and replace all instances of a logo.

Windows installer: Download

There are two possible workflows:

Pretrained model

You print / put our default discoball logo on your canvases and use the pretrained .swp file to replace it with arbitrary content. Please download the Sample Project and check the demo compositions. The default logo and .swp file are included.

Custom model

You order us to train a .swp file for your custom logo. All we need is one image of the logo. The training takes ~1 day and afterwards you can replace your custom logo with different content. Please reach out via support [at] blaceplugins [dot] com to order custom model training.

Parameters

SwapFile

Set the .swp file here. A .swp file is an AI model that was trained on a specific set of logos to learn how to replace them.

Replace Layer

The layer you want to replace the detected logos with.

Detection Confidence

The confidence with which the detection AI will recognize a logo. Higher values are more picky, while lower ones might create false positives.

Output

You can choose between “Clean Plate” (removes the default logo), “Clean Plate + Logos” (default logo removed and new logo added), “Logos” (new logo on alpha) or “Rectangle” (draws a rectangle around detected logos).

Fill Mode

“Overlay” replaces the logo with a smooth layer on top of the former logo. More blurry and less flickering. “Content Aware” takes neighbouring pixels into account, allowing for replication of shadows at the cost of more flickering.

Content Aware

Overlay

Dilate Mask

Increase the area around the logo which is replaced.

Smooth Mask

Smooth the edges of the background overlay / inpaint.

Smooth Inpaint (“Content Aware” only)

Smooths the actual inpaint.

Backend & Performance

Hardware Acceleration (on GPU version of the plugin only)

Run calculations on the GPU. This will give massive speedups compared to CPU mode.

Lower Precision

Compute with reduced precision if possible. This can save up to half of the memory and give you some speedups at the cost of sometimes slightly reduced quality.

Optimize for low VRAM

Enabling this will make sure only the ai model parts which are needed for computation are kept on the GPU. This might lower VRAM usage under some settings at the cost of moving ai models in and out of GPU memory.

Samples (not available for all settings)

The number of ai samples to calculate. This will improve the models accuracy.

Parallel (only available if Samples > 2)

This will render all samples at the same time (faster), if disabled computation might be slower but require less VRAM.

Computation Tiles (not available for all settings)

Split the computation into several tiles. This can help if you run out of memory.