Downloads · 30 days
0
ACE-Step-v1.5-ONNX
LemOneLabs/ACE-Step-v1.5-ONNX
ACE-Step-v1.5-ONNX is a text-to-audio model from LemOneLabs. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. It is set up for onnxruntime. The card lists the license as apache-2.0.
ONNX export of ACE-Step/Ace-Step1.5, a text-to-music generation model using flow matching with a Diffusion Transformer (DiT).
Access
Public
Updated Jul 9, 2026
Repo size
65.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data49.4 GB · 100%
At a glance
- Task
- Text-to-Audio
- Library
- onnxruntime
- License
- apache-2.0
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026
- SHA
- 2b284512
Base models
Model card
From the Hugging Face model README
ACE-Step v1.5 — ONNX
ONNX export of ACE-Step/Ace-Step1.5, a text-to-music generation model using flow matching with a Diffusion Transformer (DiT).
Exported for WebGPU inference via ONNX Runtime Web.
Model Components
ACE-Step v1.5 consists of several components that work together:
| Component | Description | FP32 | INT4 | FP16 |
|---|---|---|---|---|
| DiT decoder | Main diffusion transformer (24 layers, 2048 hidden, 8-step turbo) | 6.3 GB | 2.1 GB | — |
| LM (1.7B) | Causal language model for lyric-conditioned generation | 7.4 GB | 5.1 GB | — |
| Text encoder (0.6B) | Qwen3-Embedding for text conditioning | 2.4 GB | 1.7 GB | — |
| Lyric encoder | 8-layer transformer for lyric embeddings | 1.6 GB | 216 MB | — |
| Timbre encoder | 4-layer transformer for reference audio timbre | 806 MB | 108 MB | — |
| VAE decoder | AutoencoderOobleck (latent → stereo 48kHz waveform) | 337 MB | — | 169 MB |
| Text projector | Linear projection (1024 → 2048) | 8 MB | — | 4 MB |
| Embed tokens | Embedding table lookup for lyrics | 621 MB | — | 311 MB |
Directory Structure
onnx/ # FP32 ONNX models (full precision, for validation)
onnx_q4/ # INT4 weight-only quantized (for WebGPU deployment)
onnx_fp16/ # FP16 models (for conv-heavy / small components)
Usage for WebGPU
For text-to-music generation without the LM, the minimum model set is:
onnx_q4/dit_decoder_q4.onnx(2.1 GB)onnx_q4/text_encoder_q4.onnx(1.7 GB)onnx_fp16/text_embed_tokens_fp16.onnx(311 MB)onnx_q4/lyric_encoder_q4.onnx(216 MB)onnx_fp16/vae_decoder_fp16.onnx(169 MB)onnx_q4/timbre_encoder_q4.onnx(108 MB)onnx_fp16/text_projector_fp16.onnx(4 MB)
Total: ~4.6 GB — fits in 8 GB VRAM on desktop GPUs.
Inference Pipeline
- Text encoding: Tokenize caption → text_encoder → text_projector
- Lyric encoding: Tokenize lyrics → embed_tokens → lyric_encoder
- Timbre encoding: Reference audio latents → timbre_encoder
- Condition packing: Concatenate and pack text + lyric + timbre embeddings (JS logic)
- Denoising loop (8 steps): DiT decoder with Euler ODE scheduler
- VAE decode: Latents → stereo 48kHz waveform
The flow-matching scheduler runs in JavaScript — only the DiT forward pass is in ONNX.
Technical Details
- Latent space: 64 channels, 25 Hz frame rate (1920x upsampling to 48kHz)
- Denoising: 8-step turbo schedule with flow matching (Euler ODE)
- Attention: Alternating full + sliding-window (128) bidirectional attention with GQA (16 query / 8 KV heads)
- Quantization: INT4 weight-only (MatMulNBits, block_size=128, symmetric)
Export Verification
All exports verified against PyTorch reference with max absolute differences:
| Component | Max Diff |
|---|---|
| VAE decoder | 9.2e-6 |
| Text encoder | 2.3e-4 |
| Embed tokens | 0.0 (exact) |
| DiT decoder | 2.2e-5 |
| LM | 3.2e-3 |
| Lyric encoder | 2.4e-5 |
| Timbre encoder | 1.7e-5 |
| Text projector | 3.6e-6 |
Attribution
This is an ONNX conversion of ACE-Step v1.5 by the ACE-Step team.
- Paper: ACE-Step: A Step Towards Music Generation Foundation Model
- Code: github.com/ace-step/ACE-Step-1.5
- License: Apache 2.0
- Task
- Text-to-Audio
- Library
- onnxruntime
- License
- apache-2.0
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026