Skip to content

Latest commit

 

History

History
31 lines (23 loc) · 1.5 KB

1_topics.md

File metadata and controls

31 lines (23 loc) · 1.5 KB
  • Introduction to generative AI for image creation and manipulation.

  • Generative AI tools for design and illustration, such as Midjourney and Stable Diffusion.

  • Example of the tool Picthing for background removal.

  • Pieter Levels' projects PhotoAI and InteriorAI.

  • Current capabilities of image generation:

    • Comparison of AI-generated images from 2022 vs. 2024.
    • Limitations in generating complex image elements.
    • Challenges in following complex prompts.
    • Example using ComfyUI for facial swaps.
  • Access and use of image models through API and hosting:

    • Platforms like Replicate and Leonardo.ai for API access.
    • RunPod for GPU access.
  • Using templates for automatic image generation for marketing purposes.

  • Limitations and advantages of prompting techniques for Midjourney and other generative models.

  • Strategies for creating prompts with keywords and reference images.

  • Applying consistency in style with meta prompts and reference images.

  • Examples of maintaining style across different graphics using ComfyUI and templates.

  • Transition to HTML-based image generation using solutions like htmlcsstoimage.

  • Combining Vision Language Models and generative graphics for dynamic image creation.

  • Overview of generative graphics in automation and specialized tools.

  • Highlight ComfyUI and HTMLCSStoImage as key tools for integration in programming.

  • Encourage exploration of tools for marketing and product processes automation.

  • Additional resources and a video demonstration for further learning.