🖼️
Pixray
  • Docs for Pixray
  • Introduction
    • Introduction to Pixray
  • Quickstart
    • Installation
    • Generating an Image
    • Using demo colabs
    • Generating online (without installation)
    • FAQ
  • Docs
    • Primary settings
    • Fine settings
    • Image control settings
    • Drawer Settings
    • Misc/Display settings
    • Losses
    • Functional video movements
    • Image filters
  • Tutorial
    • Changing drawers
    • Changing primary settings
    • Guiding output with prompts
    • Guiding output with images
    • Guiding output with losses
    • Guiding output with image filters (ColorMapper)
    • Making a video using generation frames
    • Making a video using functional movements
    • Making a video using different prompts (story mode)
    • Working with weaker machines
  • Advanced
    • Empirical testing - comparing output quality
    • Developing a custom loss
    • Developing a custom drawer
    • Developing a custom image filter
    • Developing a function video movement
    • Modifying Pixray
  • Future
    • make Image Filter subclass - colormapper as subclass
    • Guide video (move/story) within pixray
    • Batch run for images and video
Powered by GitBook
On this page
  • Why am I getting "CUDA out of memory" errors?
  • How can I get this working on an AMD GPU?
  • What royalties should I be paying?
  • NFTs
  • Other Art Projects
  • Why is my custom palette being ignored?
  • I'm having issues on Colab. What should I do?
  1. Quickstart

FAQ

PreviousGenerating online (without installation)NextPrimary settings

Last updated 3 years ago

Why am I getting "CUDA out of memory" errors?

Pixray generally requires a minimum of 8GB VRAM (with at least 16GB recommended for the best experience). If you do have enough VRAM, you can try any or all of the following: reducing the quality setting; reducing the size/scale of the image; reducing num_cuts and increasing batches to compensate.

How can I get this working on an AMD GPU?

Unfortunately, Pixray relies on CUDA and therefore currently only works on Nvidia GPUs. You can try running in CPU mode or using a provider like Colab.

What royalties should I be paying?

Feel free to reach out in the #royalties channel on Discord or to dribnet if you have any specific questions about your use case. Generally speaking, the following guidelines apply:

NFTs

"...For NFT projects pixray requests 5% of initial sales and 0.5% of resales to find further development and support server costs in making the online tools available for free. There are wallet addresses for various blockchains in the USE file in the repo; it is preferred that payments be done contractually and on-chain but if your platform does not support that then retroactive payments can be done by transfers..." - dribnet

Other Art Projects

"Currently for commercial projects that don't end up in the NFT market we are happy with attribution only..." - dribnet

Why is my custom palette being ignored?

In order to use a custom palette, you also need to set filters to lookup.

I'm having issues on Colab. What should I do?

Colab can be a little finicky at times. Trying to Restart Runtime or Factory Reset Runtime can often solve transient issues. Using Colab Pro can also help with some issues you might encounter. If all else fails, feel free to reach out to the #debugging channel on Discord.

Why am I getting "CUDA out of memory" errors?
How can I get this working on an AMD GPU?
What royalties should I be paying?
Why is my custom palette being ignored?
I'm having issues on Colab. What should I do?