But how do AI images and videos actually work? | Guest video by Welch Labs
Why Hacker News recommends it
HN uses it as a clear explainer for diffusion mechanics, such as negative prompts and faster sampling, and for joint text-image encoders.
What it is
A guest video by Welch Labs on 3Blue1Brown explaining how text-to-image and video models work. It covers CLIP, shared embedding spaces, diffusion models (DDPM, DDIM), conditioning, guidance and negative prompts.
Recommended by 1 HN commenters across 1 different months, 2025 to 2026.
What Hacker News said
Recommends dilyevsky · 2026-06 · on “Playing with Vision Embeddings”
> Because you somehow need a giant training set which describes images in natural language, no? That's definitely one way - they train a text encoder together with an image encoder on a labelled set of images. WL & 3b1b made a nice video on it: [this video]
Cites elliotto · 2025-08 · on “Training language models to be warm and empathetic makes them less reliable”
My favourite instantiation of this weird invocation is from this AI video generator, where they literally subtract the prompt for 'low quality video' from the input, and it improves the quality. [this video] I've just migrated my AI product to a different underlying model and had to redo a few of the prompts that the new model was interpreting differently. It's not obseleted, just requires a bit of migration. The improved quality of the new models outweighs any issues around prompting.
Cites pornel · 2025-09 · on “The maths you need to start understanding LLMs”
Breakthrough in image generation speed literally came from applying better differential equations for diffusion taken from statistical mechanics physics papers: [this video]