Patreon
Home / Videos / Transform Your Selfie into a Stunning AI Avatar with Stable

Transform Your Selfie into a Stunning AI Avatar with Stable Diffusion - Better than Lensa for Free

Stable Diffusion DreamBooth turns your selfies into stunning AI avatars for free in Google Colab, better than Lensa and with your photos kept private.

Published Dec 16, 2022 · 128,683 views · Watch on YouTube

Get the app and files

Stable Diffusion AI Avatars From Your Selfies: Free Lensa Alternative

Stable Diffusion AI Avatars From Your Selfies: Free Lensa Alternative

Stable Diffusion DreamBooth turns your selfies into stunning AI avatars for free in Google Colab, better than Lensa and with your photos kept private.

Chapters

  1. 0:00 Introduction and the content
  2. 2:04 How to check you have enough Google drive space
  3. 2:18 Starting to prepare Google Colab notebook for Stablediffusion Dreambooth model training
  4. 5:01 Register, login and generate Hugging Face token for training of the AI model
  5. 6:56 Continue training setup of the Stable Diffusion Dreambooth
  6. 7:41 Setting the settings of Stable Diffusion Dreambooth model
  7. 9:08 Providing our own photos to train the model to teach our own face image
  8. 11:58 How to install Paint NET for image cropping
  9. 12:12 How to crop and prepare your training images by using Paint NET
  10. 13:36 How bulk image crop online with birme net website
  11. 14:50 How to quickly check all images dimensions in a folder by using sort options (width, height) in detailed folder view
  12. 15:26 How to upload training images to Google Colab
  13. 17:53 Starting training with last settings / options
  14. 18:11 Optimal parameters for training of Stable Diffusion Dreambooth model AI
  15. 22:42 Training of the AI model done
  16. 25:55 Exiting application/notebook completely and starting again to show how to use trained model
  17. 28:00 Starting to generate AI / Lensa app magic avatars
  18. 30:20 First avatar is generated and displayed
  19. 31:14 Explanation of the positive / inference prompt input to generate avatar images
  20. 32:44 Explanation of the negative prompt input to avoid such images, guidance_scale & num_inference_steps parameter of Stable Diffusion
  21. 36:47 New avatars with different guidance_scale parameter
  22. 37:34 How to generate colored portrait avatars / profile images
  23. 38:57 Showcasing different styles of generated avatars
  24. 40:00 Debated usage of artist styles
  25. 40:26 Continue to generate more artworks
  26. 42:18 Prompt for asian style artworks like korean, or japan or anime
  27. 44:45 Long hair, different eye color version of me
  28. 46:43 Adding armor keyword
  29. 47:22 Further tuning of input prompt
  30. 51:21 Cherry picking the results
  31. 54:27 How to generate hundreds or thousands of magic avatars as a batch
  32. 55:59 Clip of ~200 Stable Diffusion AI generated avatars
  33. 57:40 Ending talk and discussion

About this video

Our Discord : https://discord.gg/HbqgGaZVmr. How to do free Stable Diffusion DreamBooth training on Google Colab for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 🥰 https://www.patreon.com/SECourses

Playlist of Stable Diffusion Tutorials, Automatic1111 and Google Colab Guides, DreamBooth, Textual Inversion / Embedding, LoRA, AI Upscaling, Pix2Pix, Img2Img:

https://www.youtube.com/playlist?list=PL_pbwdIyffsmclLl0O144nQRnezKlNdx3

In this video, I will show you how to create your own Lensa app-like magic avatars without using any third-party apps. Our method ensures 100% privacy, unlike uploading your personal photos to external apps and platforms. I am sure you have seen many people sharing their magic avatars on social media. While these paid apps use free open-source AI models, they still require payment. Additionally, AI image generation apps may keep your private photos and use them as they please. Instead of paying and trusting the goodwill of these paid apps, we will use these open-source public AI models ourselves.

I will provide step-by-step instructions, so even those with no technical expertise can follow along. We will be using Google's Colab, a free #AI platform that offers access to a powerful GPU at no cost. Therefore, this tutorial can even be completed on a mobile phone without a PC. All you need is a Gmail account. Once we train the open-source image generation model #StableDiffusion with #DreamBooth by using our own portrait images, the possibilities are endless. Unlike other applications, the method I will demonstrate does not impose any limitations on image generation. You will be able to freely compose any kind of image as many times as you desire. You can not only generate your own avatars, but also any other images you want, such as highly detailed car images or landscapes.

5 May 2025 Tested Verified Working Perfect

Google colab notebook link (ignore error messages, skip hugging face token):

https://colab.research.google.com/github/FurkanGozukara/Stable-Diffusion/blob/main/DreamBooth/ShivamShriraoDreamBooth.ipynb

Huggingface https://huggingface.co/join

Bulk image editing: https://www.birme.net

For prompts check out the comments

0:00 Introduction and the content

2:04 How to check you have enough Google drive space

2:18 Starting to prepare Google Colab notebook for Stablediffusion Dreambooth model training

5:01 Register, login and generate Hugging Face token for training of the AI model

6:56 Continue training setup of the Stable Diffusion Dreambooth

7:41 Setting the settings of Stable Diffusion Dreambooth model

9:08 Providing our own photos to train the model to teach our own face image

11:58 How to install Paint NET for image cropping

12:12 How to crop and prepare your training images by using Paint NET

13:36 How bulk image crop online with birme net website

14:50 How to quickly check all images dimensions in a folder by using sort options (width, height) in detailed folder view

15:26 How to upload training images to Google Colab

17:53 Starting training with last settings / options

18:11 Optimal parameters for training of Stable Diffusion Dreambooth model AI

22:42 Training of the AI model done

25:55 Exiting application/notebook completely and starting again to show how to use trained model

28:00 Starting to generate AI / Lensa app magic avatars

30:20 First avatar is generated and displayed

31:14 Explanation of the positive / inference prompt input to generate avatar images

32:44 Explanation of the negative prompt input to avoid such images, guidance_scale & num_inference_steps parameter of Stable Diffusion

36:47 New avatars with different guidance_scale parameter

37:34 How to generate colored portrait avatars / profile images

38:57 Showcasing different styles of generated avatars

40:00 Debated usage of artist styles

40:26 Continue to generate more artworks

42:18 Prompt for asian style artworks like korean, or japan or anime

44:45 Long hair, different eye color version of me

46:43 Adding armor keyword

47:22 Further tuning of input prompt