=================== I Ate Mushrooms =================== Introduction ============= I Ate Mushrooms is a image and noise generator based on a pretrained BIGGAN (https://github.com/huggingface/pytorch-pretrained-BigGAN). It can generate images and videos from 1000 different objects and living beings as well as interpolations and abstract variations of those images. To start, add the plugin to a solid layer. There are several modes, „Generated“, „Neural Transition“, "Frame Interpolation" and "Text-to-Image". Generated =========== Ingredients ------------------- In this section you can define the content you want to display. Choose a number of classes and assign different classes and their respective influences on the image. This way you can mix different objects. You can find a overview over the different classes here: https://www.youtube.com/watch?v=YY6LrQSxIbc Noise ------------------- The noise that influences the generated image. "Generated" uses a precoded noise function and a seed, which is also loopable (every 360°)! "Custom Layer" lets you choose another layer which then feeds the image ai with noise. Resolution ------------------- The output resolution of the model. The smaller the faster. Variety (former Creativity), Content Multiplicator (former Empty Stomach), Content Addition (former Bright Lights), Noise Multiplicator (former Funky Music), Noise Addition (former Overtired) ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Some random sliders that affect your trip through the ai's space alot. Display ------------------- Scaling ^^^^^^^^^^^^^ How the ai's output is scaled on the effects layer. Interpolation ^^^^^^^^^^^^^^^ Choose "Nearest" for a blocky appeareance, and "Bilinear" "and Bicubic" for a smooth image interpolation. Use Superresolution ^^^^^^^^^^^^^^^^^^^^^ An ai based upsampling of the image. This together with model resolution "Low" can give good and fast results. Text-to-Image ================ Use masks names to drive the image content and masks opacity to control its respective influence. Keyframing masks opacities creates interpolation. You can download a sample project `here `_. Noise ------------------- The noise that influences the generated image. "Generated" uses a precoded noise function and a seed, which is also loopable (every 360°)! "Custom Layer" lets you choose another layer which then feeds the image ai with noise. Variety (former Creativity), Content Multiplicator (former Empty Stomach), Content Addition (former Bright Lights), Noise Multiplicator (former Funky Music), Noise Addition (former Overtired) ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Some random sliders that affect your trip through the ai's space alot. Scaling ------------------- How the ai's output is scaled on the effects layer. Interpolation ------------------- Choose "Nearest" for a blocky appeareance, and "Bilinear" "and Bicubic" for a smooth image interpolation. Use Superresolution -------------------- An ai based upsampling of the image. This together with model resolution "Low" can give good and fast results. Automatic keying -------------------- Create a ai based key for the predominant object in the scene. Add text input -------------------- Adds another mask which can be used to control the images content. Backend & Performance ----------------------- .. include:: common-args.rst