Starnodes/AceStepXL_Merge

ACE Step1.5XL_TurboSFT_Merge_50-50 – Multi-Format (FP16 / FP8 / NVFP4)

Welcome to this repository! Here you will find a merged model of ACE-Step 1.5 XL Turbo and ACE-Step 1.5 XL SFT audio model in various quantization formats, optimized for different VRAM requirements—especially for use in ComfyUI.

📌 Original Model & Credits

This repository is a repack/merge based on the fantastic work of the ACE-Step team. Please visit and support the original creators here: 👉 Original ACE-Step 1.5 XL Collection

Example for Settings:

---

📂 Available Formats

Choose the format that best fits your hardware:

1. FP16 (16-Bit Half Precision)

• File Extension: .safetensors (or marked accordingly)
• Description: The uncompressed version. Offers the absolute highest audio quality but also requires the most VRAM. Ideal for high-end GPUs.

2. FP8 (8-Bit Quantization)

• File Extension: *fp8.safetensors
• Description: The perfect sweet spot. Halves the VRAM requirement compared to FP16 while keeping the audio quality nearly identical to the original. Highly recommended for most users.

3. NVFP4 (4-Bit Quantization) 🚀

• File Extension: *nvfp4.safetensors
• Description: An extremely compressed version for minimal VRAM usage.
• Important Technical Note: Converting DiT audio models to 4-bit is highly experimental. To preserve audio quality and completely prevent the Input tensor must be contiguous crash in ComfyUI, critical sensitive layers (such as bias, norm, embed_tokens, timbre_encoder, project_in, and quantizer) were not quantized and intentionally left in bfloat16. Only the heavy Transformer blocks run in 4-bit. This makes the model stable and ready to use.

---

🛠️ Usage in ComfyUI

1. Download your desired format (FP16, FP8, or NVFP4).
2. Place the file in your ComfyUI directory under models/diffusion_models (or the specific folder required by your audio node).
3. Load the model using your standard Model Loader Node.

---

Hosted by Starnodes