2026-09-08T13:46:52.660Z
ControlNet Depth — SDXL
NVIDIA GeForce RTX 5080 · 10.04s
Evidence status: CURRENT · UNCLASSIFIED
NEURALDRIFT LAB / EVIDENCE
A transparent index of recorded local executions. A catalog estimate is never presented as a physical test.
CURRENT SUCCESSFUL RUNS
Execution records whose workflow hash still matches the downloadable graph.
OBSERVED HARDWARE
Hardware profiles represented in the evidence registry.
FAILURES / BLOCKERS
Failures remain visible rather than being replaced with success-shaped fallbacks.
2026-09-08T13:46:52.660Z
NVIDIA GeForce RTX 5080 · 10.04s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T13:44:00.964Z
NVIDIA GeForce RTX 5080 · 18.10s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T13:33:43.050Z
NVIDIA GeForce RTX 5080 · 2.09s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T13:33:25.049Z
NVIDIA GeForce RTX 5080 · 2.30s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T13:31:40.613Z
NVIDIA GeForce RTX 5080 · 6.03s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T13:30:47.210Z
NVIDIA GeForce RTX 5080 · 6.03s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T04:14:12.049Z
NVIDIA GeForce RTX 5080 · 6.03s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T04:14:06.013Z
NVIDIA GeForce RTX 5080 · 6.03s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T04:13:59.978Z
NVIDIA GeForce RTX 5080 · 6.04s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T04:13:53.930Z
NVIDIA GeForce RTX 5080 · 6.04s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T04:13:47.892Z
NVIDIA GeForce RTX 5080 · 8.03s
Evidence status: CURRENT · UNCLASSIFIED
2026-09-08T04:05:04.902Z
NVIDIA GeForce RTX 5080 · 18.06s
Evidence status: CURRENT · UNCLASSIFIED
Current evidence requires a successful recorded execution and a matching workflow hash. Test dates, environment details, model hashes, artifacts, and failures are shown only when present in the source record.
Newly released models NeuralDrift has researched but not yet run. These are documented, not execution-tested — see each page for exactly what has and hasn't been verified.
DOCUMENTED
FastH3 8-Step V2 is FastVideo's (Hao AI Lab @ UCSD) distilled version of MiniMax-H3, replacing H3's diffusion transformer with a student model trained via data-free DMD2 distillation combined with VSA-H3 sparse attention, cutting inference to 8 transformer forward passes instead of H3's standard range.
Read the writeup →FUTURE PRODUCT / INTEREST ONLY
Potential production documentation built from existing workflow assets. No checkout, price, or delivery is active.
Current workflow assets: 06, 03, 01, 27, 31, 22. Missing: Pack-specific presets, Unified setup documentation, Product delivery and checkout.