Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Stable Diffusion Style Technique Comparison - Hypernetwork vs. Textual Inversion

kasukanra via YouTube

Start learning Write review
Corporate Finance Institute Ad

Finance Certifications Goldman Sachs and Amazon Teams Trust

Learn More → Scrimba Ad

Get 20% off all career paths from fullstack to AI

Learn More →

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This video compares hypernetworks and textual inversion for creating stylized character art with Stable Diffusion. It demonstrates training a hypernetwork, evaluating results in txt2img and img2img, and refining images with digital painting tools.

Syllabus

- Intro/Preview of character artwork created with the help of stable diffusion
- Some context about environment/models I'm using
- Short rundown on how to use BIRME for preprocessing
- How to train a hypernetwork
- Temporarily paused the training to change preview options
- Initial analysis of results from hypernetwork
- Comparing textual inversion and hypernetworks on TXT2IMG results
- How to enable hypernetworks
- Comparing textual inversion and hypernetworks on IMG2IMG
- Lighting in photoshop
- Bringing lightly edited image back into img2img inpaint
- Short break to show current steps in work in process
- Turning imperfections into new features using img2img inpaint
- Updated composition
- How to light the final image
- Changing the face
- Changing the face again!
- Closing thoughts

Taught by

kasukanra

Reviews

Start your review of Stable Diffusion Style Technique Comparison - Hypernetwork vs. Textual Inversion

Start learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.