Stable Diffusion · LoRA
AceStep Refine Redmond
DPO-refined LoRA adapter for ACE-Step 1.5 Turbo that improves musicality, arrangement coherence, and vocal character in text-to-audio generation.
About this model
AceStep Refine Redmond is a DPO-refined LoRA adapter built on top of ACE-Step 1.5 Turbo (acestep-v15-turbo). The model was trained through a two-stage process: 75 epochs of large-dataset LoRA fine-tuning followed by DPO refinement on the resulting adapter, achieving approximately 70% win rate in blind A/B testing against the base model. The adapter uses LoRA rank 96 with alpha 192 and a learning rate of 8e-5.
The release includes two formats: a standard PEFT adapter for regular ACE-Step workflows, and a single-file ComfyUI-compatible LoRA export. For prompting and composition, the recommended language model is acestep-5Hz-lm-4B.
Known limitations include variable behavior with sparse prompts (less stable vocal timbre), potential texture noise or high-frequency harshness in very dense arrangements, and genre-specific generalization constraints due to the preference dataset used for DPO. The model is released under MIT license.
Model details
| Category | Stable Diffusion |
|---|---|
| Subcategory | LoRA |
| Task | text-to-audio |
| Hugging Face downloads | 0 |
| Hugging Face likes | 8 |
| Data last synced | 2026-11-12 |
Learn more
Tags
peft · ace-step · lora · dpo · music-generation · audio-generation · text-to-audio · text2audio · acestep-v15-turbo · acestep-5hz-lm-4b
Explore the source
How to use it
Load the adapter with its base model in ComfyUI, Automatic1111 or another UI that loads LoRA files, then put the prompt in the positive prompt.