Humaneness Voice Large 1.5 Alpha · prompting manual

Two frozen models. Exact instructions, matched seeds and complete take distributions. Find a promising recipe quickly, then inspect its limitations and listen.

Model, weights and inference code Pinned revision

Which CFG strength should I use?

Start around 2–2.5 for strong steering, not as a universal optimum. CFG 1 already uses the full conditional emotional prompt: it does not mean neutral or unprompted speech. These selected-CFG versus CFG-1 comparisons keep wording fixed, with 100 takes per arm across English/German, five seeds and both reference conditions.

Humaneness Voice Large 1.5 AlphaAnger and controlled ranting1.50.423 → 0.563Matched takes and quality diagnostics
Humaneness Voice Large 1.5 AlphaIntelligible intimate whispering2.00.310 → 0.507Matched takes and quality diagnostics

The target score is the normalized EARS steering objective printed on the scenario: anger here combines anger and ranting, whereas whisper uses the whisper head. It is not an emotion probability. Higher steering modestly reduced Content Enjoyment in these comparisons; intelligibility and identity must still be checked.

Could CFG 4–5 be better? Exploratory shock/transformation probes reached high target scores at 3–5, but their wording also changed. They do not isolate the CFG effect or demonstrate reliable nonverbal bursts. For a new task compare 1, 2, 2.5 and 3 with identical wording, text, reference, seed and frame cap; use 4–5 as explicitly labeled stress tests. No global best value for all 40 emotions has been established.

The ongoing full study adds a fixed-wording CFG sweep at 1, 1.25, 1.5, 2, 2.5 and 3. Its completed evidence will appear on the target pages. Machine-readable CFG guidance.

Model identity and correct loading

The released original1.3base plus its final cumulative rank128RL adapter once. Do not merge it twice.

Both models are frozen throughout these searches. They are not newly trained checkpoints. Exact GENERAL/SCRIPT format, reference limits and CFG code.

Anger and controlled ranting

2200 evaluated takes across 22 recipe cells.

Best observed starting point: repair-canonical_both, CFG 1.5.

CANONICAL

Unexpected ice-water shock

5100 evaluated takes across 51 recipe cells.

Best observed starting point: creative-cfg-five-stress, CFG 5.

CANONICAL

Anger · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Awe · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Disgust · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Doubt · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p09, CFG 2.5.

CANONICAL

Elation · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p07, CFG 1.5.

CANONICAL

Fear · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Longing · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Pain · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Pride · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Relief · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p01, CFG 1.

CANONICAL

Sadness · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Shame · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p05, CFG 2.5.

CANONICAL

Teasing · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Triumph · pure emotion

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Begging for mercy

900 evaluated takes across 9 recipe cells.

Best observed starting point: g0-p06, CFG 3.

CANONICAL

Practical interpretation

Anger benefits from an audible intention and physical delivery cues; whispering should specify breath, restraint and intelligibility rather than only requesting low volume. These are hypotheses supported by the listed development examples, not universal guarantees. Burst-heavy scenes remain harder, and their detector/timing limitations are shown beside the recipes.