From a005f37f00447e8cb0994506ee1e999d40eb16b4 Mon Sep 17 00:00:00 2001 From: Morpheus Date: Wed, 14 Oct 2026 16:44:45 +0000 Subject: [PATCH] Document duration-based Continuum runtime estimates --- .../R2V/minimax/continuum-tiled/README.md | 21 +++++++++++++++++++ .../R2V/minimax/continuum-tiled/tests.json | 6 +++++- .../minimax/continuum-tiled/variables.json | 7 +++++++ 3 files changed, 33 insertions(+), 1 deletion(-) diff --git a/optimized/R2V/minimax/continuum-tiled/README.md b/optimized/R2V/minimax/continuum-tiled/README.md index 02f8269..746c9ce 100644 --- a/optimized/R2V/minimax/continuum-tiled/README.md +++ b/optimized/R2V/minimax/continuum-tiled/README.md @@ -112,6 +112,27 @@ count at two and increases `chunk_seconds` from 6 through 10. The bypass counterparts use the same settings. This shows whether longer individual clips are viable before combining them into 30-second projects. +## Runtime planning + +The latest observed reference is **18 minutes for one 4-second chunk**. Until +more measurements are available, the monitoring estimate is: + +`expected minutes = 18 × (total generated seconds ÷ 4) + 5-minute buffer` + +Examples: + +| Generated duration | Estimated render | Monitoring window | +|---:|---:|---:| +| 4s | 18m | 23m | +| 5s | 22.5m | 28m | +| 8s | 36m | 41m | +| 20s | 90m | 95m | +| 30s | 135m | 140m | + +These are planning windows, not performance guarantees. Each completed test +must replace its estimate with the measured runtime and the model should be +recalibrated if multi-clip scaling is not approximately linear. + The bypass series uses the identical seed, references, prompt text, model, samplers, scheduler, upscale settings, tile geometry, and chunk plan. Only the Spectrum path changes. Results should be compared in pairs: CT-01 vs CT-B01, diff --git a/optimized/R2V/minimax/continuum-tiled/tests.json b/optimized/R2V/minimax/continuum-tiled/tests.json index caf4d1f..1876212 100644 --- a/optimized/R2V/minimax/continuum-tiled/tests.json +++ b/optimized/R2V/minimax/continuum-tiled/tests.json @@ -13,7 +13,11 @@ "upscale_denoise": 0.2, "upscale_cfg": 1.0, "tile": "1056x640 with 96px overlap and 32px fade", - "references": ["character-reference.png", "scene-reference.png"] + "references": ["character-reference.png", "scene-reference.png"], + "runtime_estimate": { + "observed_single_chunk": "4 seconds took 18 minutes", + "formula": "18 * (total_generated_seconds / 4) + 5 buffer minutes" + } }, "tests": [ {"id":"CT-01","purpose":"2-chunk compact prompt smoke test","prompt_variant":"compact","chunks":2,"chunk_seconds":4,"target_duration_seconds":8,"workflow":"workflow.json","status":"running","prompt_id":"9c31d895-8ccf-4dd2-aefc-da13938f7418"}, diff --git a/optimized/R2V/minimax/continuum-tiled/variables.json b/optimized/R2V/minimax/continuum-tiled/variables.json index 8a75689..ee9fdaa 100644 --- a/optimized/R2V/minimax/continuum-tiled/variables.json +++ b/optimized/R2V/minimax/continuum-tiled/variables.json @@ -25,5 +25,12 @@ "latent_upscaler": "minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors" }, "allowed_test_variables": ["prompt_variant", "chunks", "chunk_seconds"], + "runtime_estimate": { + "observed_single_chunk_seconds": 4, + "observed_single_chunk_minutes": 18, + "safety_buffer_minutes": 5, + "formula": "18 * (total_generated_seconds / 4) + 5", + "note": "Planning estimate only; record actual runtime for every result and recalibrate if scaling is not linear." + }, "target_duration_seconds": 20 }