You can deploy this model and start earning money today!

terminusresearch/
minimax-music3-training-tournament-round1

Name: minimax-music3-training-tournament-round1
Availability: InStock

MiniMaxAI/MiniMax-Music3

adapter

apache-2.0

Views

No views yet

MiniMax Music 3 training tournament round 1

A central comparison of MiniMax Music 3 language-model LoRA tournament round 1 runs. The previous campaigns are preserved below, followed by the Caption v2 training-window and singer-tag comparisons. Tournament and prompt sections are collapsed so individual audio comparisons can be opened as needed.

The card stores 2,144 FLAC renders directly in this repository. Each comparison holds its lyrics, caption conditions, LoRA-strength sweep, and random stream constant within that tournament.

Tournament overview

tournament	training window	regularisation	legs	checkpoints	renders
Previous tournament: original objective comparison	Original campaign	None	4	4	256
Full song without regularisation	Full song	None	4	9	576
Random windowing + regularisation	Random 128-frame	50% parent-teacher	3	9	432
Caption v2: training-window comparison	Random 128-frame and full song	None	4	10	400
Caption v2: singer-tag comparison	Random 128-frame and full song	None	4	10	480

Machine-readable comparison manifest

Previous tournament: original objective comparison (256 renders)

The original 1,000-step Vanilla, XM, NextLat, and NextLat + XM comparison.

All renders use a 40-second maximum duration, 30 flow steps, flow CFG 1.7, and seed 20260822. MiniMax Music 3 may end a song before the duration cap.

Training legs

The source model repos were consolidated into this repository; audio renders are stored below each comparison.

Vanilla: soad-mm3-vanilla-20260822
Explorative Modeling (XM): soad-mm3-xm-20260822
NextLat: soad-mm3-nextlat-20260822
NextLat + XM: soad-mm3-nextlat-xm-20260822

No trigger word / off-genre descriptors

Caption:

Alternative pop-jazz, 102 BPM, brushed drums, upright bass, clean electric piano, airy male vocals, smooth verse-chorus songwriting, restrained dynamics, polished intimate mix.

LoRA strength 0.25

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Trigger word only

Caption: system of a down, soad style music

LoRA strength 0.25

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Matching descriptors, no trigger word

Caption:

Lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Trigger word + matching descriptors

Caption:

system of a down, soad style music, lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 200	step 500	step 700	step 1000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Full song without regularisation (576 renders)

AdamW 8e-5, full-song training windows, no caption dropout, and no regularisation set.

All renders use a 40-second maximum duration, 30 flow steps, flow CFG 1.7, and seed 20260822. MiniMax Music 3 may end a song before the duration cap.

Training legs

Vanilla: soad-mm3-vanilla-20260823-10k-adamw8e-5-fullsong-nocapdrop
Explorative Modeling (XM): soad-mm3-xm-20260823-10k-adamw8e-5-fullsong-nocapdrop
NextLat: soad-mm3-nextlat-20260823-10k-adamw8e-5-fullsong-nocapdrop
NextLat + XM: soad-mm3-nextlat-xm-20260823-10k-adamw8e-5-fullsong-nocapdrop

Run note: These four runs resumed their learned LoRA weights from checkpoint 500 with fresh optimizer, sampler, and RNG state after the original local trainer state was lost.

No trigger word / off-genre descriptors

Caption:

Alternative pop-jazz, 102 BPM, brushed drums, upright bass, clean electric piano, airy male vocals, smooth verse-chorus songwriting, restrained dynamics, polished intimate mix.

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Trigger word only

Caption: system of a down, soad style music

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Matching descriptors, no trigger word

Caption:

Lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Trigger word + matching descriptors

Caption:

system of a down, soad style music, lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
Explorative Modeling (XM)
NextLat
NextLat + XM

Random windowing + regularisation (432 renders)

AdamW 8e-5, random 128-frame windows, 50% parent-teacher regularisation, and no caption dropout.

All renders use a 40-second maximum duration, 30 flow steps, flow CFG 1.7, and seed 20260822. MiniMax Music 3 may end a song before the duration cap.

Training legs

Vanilla: soad-mm3-vanilla-20260823-10k-adamw8e-5-randwin128-reg128-nocapdrop
NextLat: soad-mm3-nextlat-20260823-10k-adamw8e-5-randwin128-reg128-nocapdrop
NextLat + XM: soad-mm3-nextlat-xm-20260823-10k-adamw8e-5-randwin128-reg128-nocapdrop

No trigger word / off-genre descriptors

Caption:

Alternative pop-jazz, 102 BPM, brushed drums, upright bass, clean electric piano, airy male vocals, smooth verse-chorus songwriting, restrained dynamics, polished intimate mix.

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

Trigger word only

Caption: system of a down, soad style music

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

Matching descriptors, no trigger word

Caption:

Lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

Trigger word + matching descriptors

Caption:

system of a down, soad style music, lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.50

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 0.75

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

LoRA strength 1.00

training leg	step 1000	step 2500	step 4000	step 5000	step 6000	step 7000	step 8000	step 9000	step 10000
Vanilla
NextLat
NextLat + XM

Caption v2: training-window comparison (400 renders)

AdamW 8e-5 and no regularisation, comparing Vanilla and NextLat + XM with random 128-frame and full-song windows.

All renders use a 40-second maximum duration, 30 flow steps, flow CFG 1.7, and seed 20260822. MiniMax Music 3 may end a song before the duration cap.

Training legs

Vanilla, random window: soad-mm3-vanilla-randwin128-20260823-5k-adamw8e-5-capv2-noreg
NextLat + XM, random window: soad-mm3-nextlat-xm-randwin128-20260823-5k-adamw8e-5-capv2-noreg
Vanilla, full song: soad-mm3-vanilla-fullsong-20260823-5k-adamw8e-5-capv2-noreg
NextLat + XM, full song: soad-mm3-nextlat-xm-fullsong-20260823-5k-adamw8e-5-capv2-noreg

Run note: Checkpoint coverage differs by leg; empty table cells were not rendered.

No trigger word / off-genre descriptors

Caption:

Alternative pop-jazz, 102 BPM, brushed drums, upright bass, clean electric piano, airy male vocals, smooth verse-chorus songwriting, restrained dynamics, polished intimate mix.

LoRA strength 0.25

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.50

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.75

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 1.00

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

Trigger word only

Caption: system of a down, soad style music

LoRA strength 0.25

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.50

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.75

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 1.00

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

Matching descriptors, no trigger word

Caption:

Lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.50

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.75

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 1.00

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

Trigger word + matching descriptors

Caption:

system of a down, soad style music, lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.50

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 0.75

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

LoRA strength 1.00

training leg	step 1500	step 2000	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—	—	—
NextLat + XM, full song		—	—	—	—	—	—	—

Caption v2: singer-tag comparison (480 renders)

The same four Caption v2 legs evaluated with explicit Serj and Daron section assignments.

All renders use a 40-second maximum duration, 30 flow steps, flow CFG 1.7, and seed 20260822. MiniMax Music 3 may end a song before the duration cap.

Training legs

Vanilla, random window: soad-mm3-vanilla-randwin128-20260823-5k-adamw8e-5-capv2-noreg
NextLat + XM, random window: soad-mm3-nextlat-xm-randwin128-20260823-5k-adamw8e-5-capv2-noreg
Vanilla, full song: soad-mm3-vanilla-fullsong-20260823-5k-adamw8e-5-capv2-noreg
NextLat + XM, full song: soad-mm3-nextlat-xm-fullsong-20260823-5k-adamw8e-5-capv2-noreg

Run note: Checkpoint coverage differs by leg; empty table cells were not rendered.

No trigger word / off-genre descriptors

Caption:

Alternative pop-jazz, 102 BPM, brushed drums, upright bass, clean electric piano, airy male vocals, smooth verse-chorus songwriting, restrained dynamics, polished intimate mix.

LoRA strength 0.25

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.50

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.75

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 1.00

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

Trigger word only

Caption: system of a down, soad style music

LoRA strength 0.25

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.50

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.75

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 1.00

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

Matching descriptors, no trigger word

Caption:

Lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.50

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.75

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 1.00

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

Trigger word + matching descriptors

Caption:

system of a down, soad style music, lilting hypnotic arpeggios, a gentle melodic mid-tempo groove with layered harmonies, sudden explosive distorted riffs, unstable meter changes, theatrical male vocals, tightly syncopated bass and drums, abrupt shifts between fragile verses and frantic heavy choruses.

LoRA strength 0.25

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.50

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 0.75

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

LoRA strength 1.00

training leg	step 2500	step 3000	step 3500	step 4000	step 4500	step 5000
Vanilla, random window
NextLat + XM, random window
Vanilla, full song	—	—	—	—	—	—
NextLat + XM, full song			—	—	—	—

Evaluation lyrics

The original comparison lyrics are shared by the first four tournaments. The latest singer-tag comparison uses its own section-assigned lyric sheet.

Show lyrics

text

[Intro]
Count the teeth in the traffic light
Paint the silence ultraviolet

[Verse 1]
Paper crowns on the factory floor
Everybody wants a little more
Wind-up prophets in a checkout line
Selling borrowed seconds back as time

[Pre-Chorus]
Turn the dial, divide the sky
Ask the wires to tell us why

[Chorus]
Wake up the walls, let the ceiling shake
We built a feast from a plastic lake
Hands in the air while the engines stall
Who signed the order to swallow it all?

[Verse 2]
Velvet sirens in the avenue
Paint every warning a pleasant blue
I fed my shadow to the voting machine
It came back polished, quiet, and clean

[Bridge]
Softly, softly, count to four
Kick down the arithmetic door
One for the hunger, two for the show
Three for the ones who already know

[Final Chorus]
Wake up the walls, let the ceiling shake
We built a feast from a plastic lake
Hands in the air while the engines stall
Who signed the order to swallow it all?

[Outro]
Count the teeth
Kill the light
Carry the silence
Into the night

Show singer-tag comparison lyrics

text

[Verse 1: Serj Tankian]
Why don't you ask the kids at Tiananmen Square?
Was fashion the reason why they were there?
They disguise it, hypnotize it
Television made you buy it

[Chorus: Daron Malakian]
I'm just sitting in my car and
Waiting for my

[Verse 2: Daron Malakian]
She is scared that I will take her away from there
Dreams and her country left with no one there
Mesmerized, the signal bends the truth
The broadcast paints a blindfold on the youth

[Chorus: Serj Tankian]
I'm still waiting by the dashboard
Watching for the signal
I'm still waiting by the dashboard
Waiting for my girl

[Instrumental Break]

[Chorus: Daron Malakian]
I'm still waiting by the dashboard
Waiting for my girl
I'm still waiting by the dashboard
Waiting for my girl

Inference notes

The four LoRA strengths were evaluated in one batched pass with a shared random stream. NextLat's predictor and XM's route embeddings are auxiliary training modules and were not used at inference. The generated audio remains hosted in the source model repositories linked above.

terminusresearch/minimax-music3-training-tournament-round1

MiniMax Music 3 training tournament round 1

Tournament overview

No trigger word / off-genre descriptors

Trigger word only

Matching descriptors, no trigger word

Trigger word + matching descriptors

No trigger word / off-genre descriptors

Trigger word only

Matching descriptors, no trigger word

Trigger word + matching descriptors

No trigger word / off-genre descriptors

Trigger word only

Matching descriptors, no trigger word

Trigger word + matching descriptors

No trigger word / off-genre descriptors

Trigger word only

Matching descriptors, no trigger word

Trigger word + matching descriptors

No trigger word / off-genre descriptors

Trigger word only

Matching descriptors, no trigger word

Trigger word + matching descriptors

Evaluation lyrics

Inference notes

terminusresearch/
minimax-music3-training-tournament-round1