Model reference · open weights
ACE-Step-1.5 is an open-weight audio or speech model from Comfy-Org. ACE-Step-1.5 (BF16) weighs 63.1 GB; the smallest configuration that runs it is H100 80 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
ACE-Step-1.5 is a text-to-audio model developed by Comfy-Org. The card describes it as repackaged model files intended for use with ComfyUI. It is distributed under the apache-2.0 licence.
Summary of the Comfy-Org/ACE-Step-1.5 model card, 2026-10-28
What it is
| Released by | Comfy-Org |
|---|---|
| Released | 2026-02-03 |
| VRAM | 63.1 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB … L40S 48 GB | does not fit | |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Repackaged model files for ComfyUI.
Original model repository: https://huggingface.co/ACE-Step/Ace-Step1.5
Place the files in the following folders:
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 checkpoints/
│ │ └── ace_step_1.5_turbo_aio.safetensors
│ ├── 📂 diffusion_models/
│ │ ├── acestep_v1.5_base.safetensors
│ │ ├── acestep_v1.5_turbo.safetensors
│ │ ├── acestep_v1.5_xl_base_bf16.safetensors
│ │ ├── acestep_v1.5_xl_sft_bf16.safetensors
│ │ └── acestep_v1.5_xl_turbo_bf16.safetensors
│ ├── 📂 text_encoders/
│ │ ├── qwen_0.6b_ace15.safetensors
│ │ ├── qwen_1.7b_ace15.safetensors
│ │ └── qwen_4b_ace15.safetensors
│ ├── 📂 vae/
│ │ └── ace_1.5_vae.safetensors
These are repackaged files to work with ComfyUI, original model repo is: https://huggingface.co/ACE-Step/Ace-Step1.5
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → ACE-Step 1.5 Music Generation Workflow, and choose this model's file in its model loader.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the model (10.8 GB)
get Comfy-Org/ACE-Step-1.5 checkpoints/ace_step_1.5_turbo_aio.safetensors diffusion_models
get Comfy-Org/ACE-Step-1.5 split_files/text_encoders/qwen_0.6b_ace15.safetensors text_encoders
get Comfy-Org/ACE-Step-1.5 split_files/vae/ace_1.5_vae.safetensors vae
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST, PORT and BOOKING are your machine's, from its page in the console
ssh -o HostKeyAlias=axforge-BOOKING -o StrictHostKeyChecking=accept-new -L 8188:localhost:8188 dev@HOST -p PORT