Ablation checkpoint for the AffectScore rank sweep. Identical to the full r=32 model except Layer 2 style-text descriptor is removed from the conditioning prompt. The Layer 1 V-A mood-word prompt is retained. CLAP auxiliary monitoring is additionally disabled (redundant since L_CLAP carries zero gradient to LoRA weights regardless of λ, but disabled for consistency).

This checkpoint isolates the contribution of the Layer 2 style-text descriptor. It is not intended for production use.

Code and Colab notebooks: github.com/LeeTgk/affectscore (link active after publication)

Training dataset: https://zenodo.org/records/21830658

All metrics computed on 200 held-out clips at 40 diffusion steps.

CLAP-score is undefined for this variant (no style-text reference string).

Training loss: L_diff = 1.1713 at epoch 50 (Δ = +0.0047 above full r=32).

See affectscore-ace-step-r32-20260629 for the full variant table and evaluation discussion.

Citation will be added once the paper is published. If you use this model before then, please link to this repository.