<h3 id="mmaudio-adapter-for-comfyui">MMaudio Adapter for ComfyUI</h3>A local notebook for learning:<a target="_blank" rel="ugc" href="https://civarchive.com/models/2487771/mmaudio-adapter-trainer">https://civarchive.com/models/2487771/mmaudio-adapter-trainer</a><hr />0. Download the release ZIP from Civitai and extract it.You should get the custom node folder, workflow JSON, and repo patch files from the extracted archive.<hr />1. Place <code>custom_nodes/ComfyUI-MMAudio-LoRA/</code> under your ComfyUI installation.<hr />2. Install the custom node requirements in the same Python environment used by ComfyUI:<code>python -m pip install -r .\custom_nodes\ComfyUI-MMAudio-LoRA\requirements.txt</code><hr />3. Place the workflow JSON and load it from the ComfyUI UI.<hr />4. Clone the official MMAudio repository inside the ComfyUI folder:<code>cd ComfyUI</code><code>git clone https://github.com/hkchengrex/MMAudio.git</code><code>cd MMAudio</code><code>python -m pip install -e .</code><hr />5. Apply the repo patch files from the extracted ZIP:- <code>eval_utils.py</code> -&gt; <code>ComfyUI\MMAudio\mmaudio\eval_utils.py</code>- <code>lora.py</code> -&gt; <code>ComfyUI\MMAudio\mmaudio\model\lora.py</code>- <code>networks.py</code> -&gt; <code>ComfyUI\MMAudio\mmaudio\model\networks.py</code>- <code>precision.py</code> -&gt; <code>ComfyUI\MMAudio\mmaudio\utils\precision.py</code><hr />6. Restart ComfyUI completely.<hr />7. Load the workflow and test base generation first without LoRA.- <code>num_steps</code> must be &gt;= 1- <code>repo_root</code> can usually be left blank- if auto-detection fails, set it to <code>ComfyUI\MMAudio</code><hr />8. To use a LoRA, place the LoRA file in <code>ComfyUI\input\</code> and set the file name in <code>MMAudio LoRA Loader -&gt; lora_path</code>.Example:- file: <code>ComfyUI\input\aw_large_44k_lora_last.safetensors</code>- lora_path: <code>aw_large_44k_lora_last.safetensors</code>Trainer:<a target="_blank" rel="ugc" href="https://civarchive.com/models/2487771/mmaudio-adapter-trainer">https://civarchive.com/models/2487771/mmaudio-adapter-trainer</a>

Files with SHA256: 4abd7080103186338b788ee18ddd734e51afabe526fa8d2b094c3a1d7b97e596