Realism isn’t a look—it’s the consistent physics of causes across geometry, light, and camera capture.
Previous · Part 5
Lens Logic for AI Prompts: How Focal Length Rewrites Your Scene
Next · Part 7
Exposure as Realism: Dynamic Range & Sensor Character for Images That Don’t Blink
This builds on Part 5: Lens Logic for AI Prompts: How Focal Length Rewrites Your Scene
Continue with Part 7: Exposure as Realism: Dynamic Range & Sensor Character for Images That Don’t Blink
The problem with “realistic blur”
Most AI images don’t fail because they blur. They fail because their blur is narrative, not physical.
A depth of field (DoF) that “reads as real” has three traits:
- It’s tied to a believable focus plane.
- Its blur changes smoothly with distance (not instantly, not uniformly).
- It behaves like a lens—including edge softness, highlight character, and the way texture survives within the focus region.
What “AI blur” looks like (and why)
Here are the failure patterns that give the game away:
- Hard focus bands: crisp → blurry with a noticeable step.
- Over-universal blur: everything beyond focus loses detail equally.
- Texture evaporation: skin, fabric, and signage dissolve too quickly.
- Wrong highlight physics: bokeh circles appear as “painted blobs” with no lens personality.
- Focus disbelief: the most salient subject is slightly soft in a way a real photographer would never tolerate.
The lens-to-geometry rule: focus plane decides everything
In real photographs, only one plane is perfectly sharp (ideally). Everything else is a function of:
- Focus distance (where the lens is focused)
- Focal length / field of view (how strongly blur separates)
- Aperture (how wide the lens is letting light through)
- Distance to subject and background (the geometry of separation)
AI often blurs as if the world is compressed. Your job is to restore credible geometry via prompt specifics.
Unlock the full applied series
Get all 15 parts of The Physics of Better AI Images — 92 min read · 18,266 words across the full sequence.
Inside the series
Parts 1-4: Constraints make it real
Parts 5-9: Camera causes, not vibes
Parts 10-12: Surfaces, framing, and truth priority
Parts 13-14: Repair and recipe workflows
Part 15: Master Prompt Sheet
Realism isn’t a look—it’s the consistent physics of causes across geometry, light, and camera capture.
Membership gives access to subscriber dispatches and ongoing Pen & Muse tools. This paid series is sold separately.
If this resonates, see how to apply it to your own work with the interactive Dispatch agent.
Be first to like this dispatch
