ComfyUI: CFG-distilled sampling recipe (BasicGuider, shift 12/3) + load-console and strength-0 diagnostics

README.md

@@ -125,12 +125,23 @@ non-rotated base:
    `MiniMaxH3ImageToVideo` / your sampler.
 3. Strength **1.0** (useful range 0.7–1.2).
 
+**Sampling recipe** — H3 is CFG-distilled, so SDXL/Flux habits will degrade it
+with or without a LoRA: use **BasicGuider** (not CFGGuider), `res_multistep` +
+`simple`, ~**20 steps**, **video shift 12 / audio shift 3** (the MiniMax H3
+Sigma Shift node). Stay near 1 MP (very low resolutions are unstable) and keep
+prompts to a single shot.
+
 **Stacking with a turbo LoRA:** drop this one to **0.4–0.6** — the two
 perturbations add, and 4-step turbo has little headroom. (The `turbo_mode`
 checkbox occupies its own LoRA slot; add a second `LoraLoaderModelOnly` for
 this one.) 4-step turbo also softens the tape grain — ~20–25 full-precision
-steps show the style best. Stay near 1 MP (very low resolutions are unstable)
-and keep prompts to a single shot.
+steps show the style best.
+
+**If it looks wrong, two 2-minute checks:** (1) watch the console at load —
+this LoRA should patch with **zero** "lora key not loaded" lines; (2) on a
+quantized base, load the LoRA at **strength 0.0** and compare to no-LoRA — if
+output degrades even at 0.0, the damage is the quantize→merge→requantize
+round-trip on your base checkpoint, not this LoRA: switch to the bf16 base.
 
 `vh5tape-comfyui.safetensors` is an optional convenience build: bit-identical
 weights plus explicit `.alpha` tensors (= rank, scale 1.0) and the base-model