Prompt Library
Prompts that outlive the model they were written for.
Guides for generative image and video models, written against the models we actually run — and dated, so you can tell what still holds.
Foundations
Holds across every model
Prompt Basics
How a prompt is put together, and why small wording changes swing the result
3 guides →
Camera & Composition
Shot size, camera angle, lens language and movement — the vocabulary that works across every image and video model
4 guides →
Workflows
Chaining models together — text-to-image to image-to-video, references, upscaling and cleanup
1 guide →
Model guides
Pinned to a version & dated
Video Models
Seedance 2.0
Veo 3.1
Kling
Seedance 2.5
Image Models
1 guide →
Nano Banana Pro
GPT Image 2
Flux 2
Seedream 4.5
Latest
11 published
Camera & Composition
Shot Sizes, And Why "Close-Up" Isn't Specific Enough
Wide, medium, close-up, extreme close-up. How much of the subject is in frame is the single most reliable control you have over an AI shot.
11 Aug 2026
6 min read
Prompt Basics
Change One Thing: How To Iterate On A Prompt
Rewriting the whole prompt after a bad result teaches you nothing. Changing one clause at a time is slower per attempt and far faster overall.
11 Aug 2026
5 min read