Blog
Field reports, mechanisms, self-reports and releases. Every measured number carries its date and the conditions it was measured under — and the misses are published next to the hits.
Five hosts with the same GPU model regenerated one image. The results fell into exactly two byte-identical files — and the CPU vendor, not the driver, sorted them.
Read it →A folder of verified files is not a working environment. Three host-side ways a restore can pass every checksum and still fail — and what the pre-check refuses now.
Self-reportsEvery file matched, the image regenerated — on the machine that packed it. The next day a clean machine couldn't install its dependencies. What went wrong and what the tool does now.
Self-reportsThe driver floor in our pre-check was copied from a real vendor table — for installing the CUDA toolkit, which we never do. It took three corrections and one paid-for measurement to get one number honest.
Field reportsSame GPU model: the regenerated video is literally the same file. Different model — even same architecture: a uniform ~0.94 plateau. And the 0.9814 mystery is solved: it was the CPU vendor.
Field reportsA workflow with 3 custom nodes and a LoRA is captured and revived intact — including a node that was already broken — while new data forces honest revisions to Vol. 1.
Field reportsWe packed one ComfyUI + SDXL environment, destroyed the machine, and revived it 26 times across 2 clouds, 7 datacenters, and 6 GPU types — every copy verified byte-for-byte.
Field log
Real runs, real hardware, real numbers — including the ones that failed. No schedule we can't keep.