Basic concepts on AIGC
  • About the course materials
  • General Course Format and Strategies
  • Introduction
  • Foundations for AIGC
    • Computers and content generation
    • A brief introduction to AI
      • What AI is?
      • What ML is?
      • What DL is?
      • Discriminative AI vs. Generative AI
  • Generative AI
    • Introduction to Generative AI
      • Going deeper into Generative AI models
  • Deep Neural Networks and content generation
    • Image classification
    • Autoencoders
    • GAN: Generative Adversarial networks
    • Transformers
    • Diffusion models
      • Basic foundations of SD
  • Current image generation techniques
    • GANs
  • Current text generation techniques
    • Basic concepts in NLP in Large Language Models (LLMs)
    • How chatGPT works
  • Prompt engineering
    • Prompts for LLM
    • Prompts for image generators
  • Current AI generative tools
    • Image generation tools
      • DALL-E 2
      • Midjourney
        • More experiments with Midjourney
        • Composition and previous pictures
        • Remixing
      • Stable diffusion
        • Dreambooth
        • Fine-tuning stable diffusion
      • Other solutions
      • Good prompts, img2img, inpainting, outpainting, composition
      • A complete range on new possibilities
    • Text generation tools
      • OpenAI GPT
        • GPT is something really wide
      • ChatGPT
        • Getting the most from chatGPT
      • Other transformers: HuggingFace
      • Other solutions
      • Making the most of LLM
        • Basic possibilities
        • Emergent abilities of LLM
    • Video, 3D, sound, and more
    • Current landscape of cutting-edge AI generative tools
  • Use cases
    • Generating code
    • How to create good prompts for image generation
    • How to generate text of quality
      • Summarizing, rephrasing, thesaurus, translating, correcting, learning languages, etc.
      • Creating/solving exams and tests
  • Final topics
    • AI art?
    • Is it possible to detect AI generated content?
    • Plagiarism and copyright
    • Ethics and bias
    • AI generative tools and education
    • The potential impact of AI generative tools on the job market
  • Glossary
    • Glossary of terms
  • References
    • Main references
    • Additional material
Powered by GitBook
On this page
  1. Current AI generative tools
  2. Image generation tools
  3. Stable diffusion

Dreambooth

PreviousStable diffusionNextFine-tuning stable diffusion

Last updated 2 years ago

Dreambooth fine-tune the whole text-to-image model such that it learns to bind a unique identifier with a specific concept (object or style). As a result, the generated images is more personalized to the object or style compared to textual inversion.

Step by step example:

Original paper:

https://towardsdatascience.com/how-to-fine-tune-stable-diffusion-using-dreambooth-dfa6694524ae
https://dreambooth.github.io/
DreamBooth —How Google hacks Diffusion Model to generate personalized photosMedium
GitHub - XavierXiao/Dreambooth-Stable-Diffusion: Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable DiffusionGitHub
Logo
Logo