Production-Grade Blind Evaluation: Four Pipeline Gotchas That Will Bite You
**Category:** tools | **Tier:** Workshop ($15) | **Estimated reading time:** 11 min
**Excerpt:** You wrote a script that...
Related Tutorials
Tame Your SD Output Library: Sort by Model, Then Browse
Two small scripts for anyone drowning in generated images: sort a mixed output folder into per-model subdirectories by reading each file's embedded metadata, then page through the result in a keyboard-driven 2x2 grid.
Diagnosing Intermittent Checkpoint Failures with a Tensor Health Scan
A repeatable way to track down a checkpoint that fails on some seeds and not others: write a NaN/Inf/magnitude scan, always run a control group, and learn why a clean static scan points straight at a dynamic fp16 cause.
Bake Stability Diagnostics — When Your Recipe Won't Bake
You found a perfect LoRA recipe at runtime. Tournament-tested it across multiple rounds. Picked the winner. You bake it into the checkpoint and the output is neon nightmare at every CFG. Lowering CFG doesn't help. Lighter weights don't help. Fresh base doesn't help. You've burned half a day on a recipe that won't survive being baked. Here's the diagnostic batch I use when this happens — five controlled variant bakes running in parallel, each isolating a different cause. By the time the batch finishes, you know exactly what broke (and usually it's something you couldn't have predicted from runtime behavior).