Overview
This course covers advanced techniques in Stable Diffusion, such as face and image variations, super resolution, and next frame prediction. The learning outcomes include understanding the hackability and limitations of Stable Diffusion, as well as gaining skills in image generation and editing. The teaching method involves a technical deep dive by a Senior Machine Learning Researcher, making it suitable for individuals interested in image processing and creative applications.
Syllabus
Intro
Hackability of Stable Diffusion
Limitations of Text
Image Variations
Face Variations
Image Generation
Super Resolution
Next Frame Prediction
Conclusion
Taught by
Hugging Face