Completed
Explanation of the negative prompt input to avoid such images, guidance_scale & num_inference_steps parameter of Stable Diffusion
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Transform Your Selfie into a Stunning AI Avatar with Stable Diffusion - Better Than Lensa
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction and the content
- 2 How to check you have enough Google drive space
- 3 Starting to prepare Google Colab notebook for Stablediffusion Dreambooth model training
- 4 Register, login and generate Hugging Face token for training of the AI model
- 5 Continue training setup of the Stable Diffusion Dreambooth
- 6 Setting the settings of Stable Diffusion Dreambooth model
- 7 Providing our own photos to train the model to teach our own face image
- 8 How to install Paint NET for image cropping
- 9 How to crop and prepare your training images by using Paint NET
- 10 How bulk image crop online with birme net website
- 11 How to quickly check all images dimensions in a folder by using sort options width, height in detailed folder view
- 12 How to upload training images to Google Colab
- 13 Starting training with last settings / options
- 14 Optimal parameters for training of Stable Diffusion Dreambooth model AI
- 15 Training of the AI model done
- 16 Exiting application/notebook completely and starting again to show how to use trained model
- 17 Starting to generate AI / Lensa app magic avatars
- 18 First avatar is generated and displayed
- 19 Explanation of the positive / inference prompt input to generate avatar images
- 20 Explanation of the negative prompt input to avoid such images, guidance_scale & num_inference_steps parameter of Stable Diffusion
- 21 New avatars with different guidance_scale parameter
- 22 How to generate colored portrait avatars / profile images
- 23 Showcasing different styles of generated avatars
- 24 Debated usage of artist styles
- 25 Continue to generate more artworks
- 26 Prompt for asian style artworks like korean, or japan or anime
- 27 Long hair, different eye color version of me
- 28 Adding armor keyword
- 29 Further tuning of input prompt
- 30 Cherry picking the results
- 31 How to generate hundreds or thousands of magic avatars as a batch
- 32 Clip of ~200 Stable Diffusion AI generated avatars
- 33 Ending talk and discussion
