Your imaginations is (no longer) the limit: how Generative AI empowers people to be creative

How do you get an AI to create the exact image you're imagining? Learn how sketches and poses can give you precise creative control.

#1about 3 minutes

The evolution of AI from limited to powerful image generation

Early AI art was low-resolution, domain-specific, and uncontrollable, but modern models like Stable Diffusion can now generate high-quality images from any prompt.

#2about 3 minutes

Understanding how diffusion models generate images from text

Diffusion models are trained on billions of image-text pairs to learn concepts, then generate new images by reversing a "noising" process based on a user's prompt.

#3about 2 minutes

Using AI to edit specific parts of an image

AI image editing works by masking a specific region and applying the diffusion model's denoising process only to that area, preserving the surrounding context.

#4about 5 minutes

Teaching AI to recognize specific people or styles

By creating a new "word" in the AI's vocabulary, you can train it to generate images of a specific person, object, or artistic style using a technique like Textual Inversion.

#5about 5 minutes

Guiding AI image generation with visual inputs

Instead of relying solely on text prompts, you can control the AI's output composition by providing visual inputs like sketches, pose data, or depth maps.

#6about 11 minutes

Answering questions on AI training, ethics, and ownership

The discussion covers practical topics like video generation and open-source models, as well as complex issues such as ethical risks, watermarking, and copyright ownership of AI-generated content.