Completed
Compositing the new hypernetwork output layers
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Create Stylized Vector Logo Chibi Characters with Stable Diffusion
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction
- 2 Examples of personal realistic artwork/motivation for creating heavily stylized artwork
- 3 Preview of possibilities
- 4 Materials and tools needed for the workflows
- 5 More detailed explanation of workflow
- 6 Reasoning for using Adobe Illustrator to convert raster image to vector image
- 7 Blender scene render overview
- 8 Don't use renders shot from the rear perspective
- 9 How to properly l subject for best image training
- 10 Using diffusers vs. checkpoint files
- 11 Enable git LFS to make sure large files are cloned to your machine
- 12 DreamBooth training script overview
- 13 Difference between two workflows
- 14 Method 1
- 15 Method 2
- 16 Two trained models as an experiment, left model is superior
- 17 Text prompts in AUTOMATIC1111
- 18 Finding the hero image from prompting
- 19 Creating the inpainting model from your trained model
- 20 Testing the inpainting model
- 21 Analyzing the sample outpainting outputs
- 22 Outpainting upwards
- 23 Short timelapse full timelapse in description
- 24 Using the waven chibi hypernetwork
- 25 Compositing the new hypernetwork output layers
- 26 Adobe Illustrator introduction
- 27 Image Trace Demonstration
- 28 File export options
- 29 Closing thoughts
