--- license: cc-by-nc-sa-4.0 base_model: - ACE-Step/acestep-v15-xl-turbo tags: - ace-step - audio - music-generation - vae - lora - regrind - oobleck - artifact-suppression --- ![ACEStep XL Regrind V1](assets/header.png) # ACEStep XL Regrind V1 ### Oobleck VAE · DiT Layer · Artifact Suppression Stack **Fine-tuned VAE decoder and DiT LoRA targeting the Oobleck hum artifact series at the weight level** *Alexander Allan (MDMAchine) · A&E Concepts · CC BY-NC-SA 4.0* [![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc-sa/4.0/) [![Base: ACE-Step XL Turbo](https://img.shields.io/badge/Base-ACE--Step%20XL%20Turbo-purple.svg)](https://huggingface.co/ACE-Step/acestep-v15-xl-turbo) [![VAE: v10b](https://img.shields.io/badge/VAE-v10b-green.svg)]() --- ## What is this? ACEStep XL Turbo and the Oobleck VAE produce a characteristic harmonic artifact present in all generations. The artifact has two independent origins: **VAE decoder bias** — static reconstruction bias baked into the Oobleck decoder during its original training. Present at consistent amplitude across all generations, independent of length. Characterized via Ableton EQ Eight direct measurement: | Frequency | Depth | Character | |---|---|---| | 74.4 Hz | -1.43 dB | Sub fundamental, BPM-dependent | | 94.0 Hz | -1.86 dB | Upper sub resonance | | 654–669 Hz | -12 to -15 dB | **Primary hum**, BPM shift ~2Hz/octave | | 211 Hz | ~-7 dB | 3rd harmonic | | 1090 Hz | ~-7 dB | 5th harmonic | **DiT body resonance** — accumulates over the denoising trajectory, perceptible after ~60 seconds. Hypothesized to arise from ODE manifold shearing in early denoising steps creating resonant modes in FFN activations of the decoder layers. Both components require independent treatment. Post-processing filters (like the hum notch in MD Audio VAE Tiled) address the symptom. This regrind addresses the cause at the weight level. --- ## Files ### VAE (`vae/`) | File | Size | Description | |---|---|---| | `vae/acestep_1.5_vae_Regrind_V10b-BF16.gguf` | 337 MB | VAE V10b — full-strength regrind (bf16 gguf) | | `vae/acestep_1.5_vae_Regrind_V10b.safetensors` | 337 MB | VAE V10b — full-strength regrind (safetensors) | | `vae/acestep_1.5_vae_Regrind_V10b_blend50-BF16.gguf` | 337 MB | VAE V10b — 50% blend, conservative (bf16 gguf) | | `vae/acestep_1.5_vae_Regrind_V10b_blend50.safetensors` | 337 MB | VAE V10b — 50% blend, conservative (safetensors) | | `vae/acestep_1.5_vae_Regrind_V9b-BF16.gguf` | 337 MB | VAE V9b — full-strength (bf16 gguf, previous gen) | | `vae/acestep_1.5_vae_Regrind_V9b_blend50-BF16.gguf` | 337 MB | VAE V9b — 50% blend (bf16 gguf, previous gen) | | `vae/acestep_1.5_vae_Regrind_V9b_blend50.safetensors` | 337 MB | VAE V9b — 50% blend (safetensors, previous gen) | | `vae/acestep_1.5_vae_Regrind_V7.safetensors` | 337 MB | VAE V7 — legacy (safetensors) | ### DiT base model (`dit/`) | File | Size | Description | |---|---|---| | `dit/acestep_xl_turbo_Regrind_V1.safetensors` | 9.97 GB | Full regrinded DiT base model (bf16) | | `dit/acestep_1.5_xl_turbo_regrind_v1-Q6_K.gguf` | 4.1 GB | DiT Q6_K quantized (acestep.cpp / HOT-Step) | | `dit/acestep_1.5_xl_turbo_regrind_v1-Q4_K_M.gguf` | 2.99 GB | DiT Q4_K_M quantized (acestep.cpp / HOT-Step) | | `dit/acestep_1.5_xl_turbo_regrind_v1-Q8_0.gguf` | 5.18 GB | DiT Q8_0 quantized (acestep.cpp / HOT-Step) | ### LoRA (`lora/`) | File | Size | Description | |---|---|---| | `lora/acestep_xl_turbo_lora_LayerRegrind_V7.safetensors` | 393 MB | DiT layer regrind LoRA (strength 0.25–0.50) | --- ## Which VAE should I use? **Start with `vae/acestep_1.5_vae_Regrind_V10b_blend50-BF16.gguf`** (or `.safetensors` for ComfyUI) — 50% blend between V10b regrind and the base decoder. Conservative, closest to the base model's original frequency response. Recommended for most material, especially anything spectrally dense or noisy. **Use `vae/acestep_1.5_vae_Regrind_V10b-BF16.gguf`** for full-strength V10b suppression when the blend isn't aggressive enough. **V9b variants** are the previous generation. Still valid if V10b causes any issues on your material. **V7 safetensors** is the oldest format, kept for legacy loaders. --- ## Recommended stack ``` DiT base: dit/acestep_xl_turbo_Regrind_V1.safetensors VAE: vae/acestep_1.5_vae_Regrind_V10b_blend50.safetensors (ComfyUI) vae/acestep_1.5_vae_Regrind_V10b_blend50-BF16.gguf (acestep.cpp / HOT-Step) LoRA: lora/acestep_xl_turbo_lora_LayerRegrind_V7.safetensors (strength 0.25–0.50) ``` On raw ACE-Step XL Turbo without the regrinded base: load the LoRA at 0.50–1.00. No trigger words. Standard ACE-Step prompting. --- ## Pair with MD Audio VAE Tiled For long-form generation (>30s), pair with the MD Audio VAE Tiled decoder node for ComfyUI. Handles BPM-synced tiling, dual-pass seam elimination, and post-decode spectral cleanup (Wiener denoiser, harmonic preservation crossfade, hum notch stack). The regrind addresses artifact suppression at the weight level. MD Audio VAE Tiled addresses the decode mechanics. Both together give the cleanest output. **→ [MD Audio VAE Tiled](https://github.com/MDMAchine/MD-Audio-VAE-Tiled)** --- ## Related tools | Repo | Description | |---|---| | [MD Audio VAE Tiled](https://github.com/MDMAchine/MD-Audio-VAE-Tiled) | BPM-synced tiled VAE decoder — ComfyUI + C++ + Lua | | [STORM Sampler](https://github.com/MDMAchine/STORM-Sampler) | Adaptive ODE solver, kills metallic hum at source | | [MD HAP Scheduler](https://github.com/MDMAchine/MD-HAP-Scheduler) | Physics-derived sigma schedule, HAP+TPT | | [MD Causal Scheduler](https://github.com/MDMAchine/MD-Causal-Scheduler) | Causal timestep scheduler | --- ## License Model weights are licensed under **CC BY-NC-SA 4.0**. These are derivative works of ACE-Step XL Turbo (Apache 2.0, ACE Studio / StepFun). Free for personal and research use. Commercial use requires a separate license — contact A&E Concepts. Source code for associated ComfyUI nodes, C++ headers, and Lua plugins is licensed separately under **GPL v3** in the repositories above. --- ## Citation / acknowledgment If you use these weights in your work, please credit: > Alexander Allan (MDMAchine) — ACEStep XL Regrind V1, A&E Concepts, 2026. > https://huggingface.co/mdmachine/ACEStep-XL-Regrind-V1 Base model: ACE-Step v1.5 XL Turbo — ACE Studio / StepFun (Apache 2.0). --- *© 2026 Alexander Allan (MDMAchine) · A&E Concepts*