ACE Step 1.5 XL — SFT (4B DiT) Project Hugging Face ModelScope Space Demo Discord Tech Report Model Details This is the XL (4B) SFT variant of ACE Step 1.5 — a supervised fine tuned model with ~4B parameters. SFT provides higher audio quality with CFG (Classifier Free Guidance) support for fine grained prompt adherence control. XL Architecture Parameter Value DiT Decoder hidden size 2560 DiT Decoder layers 32 DiT Decoder attention heads 32 Encoder hidden size 2048 Encoder layers 8 Total params ~4B Weights size (bf16) ~18.8 GB Inference steps 50 (with CFG) GPU Requirements VRAM Support ≥12 GB With CPU offload + INT8 quantization ≥16 GB With CPU offload ≥20 GB Without offload ≥24 GB Full quality (XL + 4B LM) All LM models (0.6B / 1.7B / 4B) are fully compatible with XL. Key Features 💰 Commercial Ready: Trained on legally compliant datasets. Generated music can be used for commercial purposes. 📚 Safe Training Data: Licensed music, royalty free/public domain, and synthetic (MIDI to Audio) data. 🎯 CFG Support: Fine tune prompt adherence with guidance scale control. 🔮 Highest Quality: SFT + 4B parameters = the highest quality variant. Quick Start Model Zoo XL (4B) DiT Models DiT Mode…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy