comfyuiaudioldm

ComfyUI AudioLDM 音频生成工作流 JSON 及使用指南 工作流 JSON（可直接导入 ComfyUI）： ```json { "last_node_id": 12, "last_link_id": 8, "nodes": [ { "id": 1, "type": "LoadAudioLDMModel", "pos": [100, 100], "size": [300, 100], "flags": {}, "order": 1, "mode": 0, "inputs": [], "outputs": [ { "name": "AUDIO_LDM_MODEL", "type": "AUDIO_LDM_MODEL", "links": [1] } ], "properties": { "model": "audioldm-s-full" } }, { "id": 2, "type": "AudioLDMTextToAudio", "pos": [500, 100], "size": [350, 200], "flags": {}, "order": 2, "mode": 0, "inputs": [ { "name": "model", "type": "AUDIO_LDM_MODEL", "link": 1 } ], "outputs": [ { "name": "AUDIO", "type": "AUDIO", "links": [2] } ], "properties": { "text": "雨声和雷声", "duration": 5.0, "guidance_scale": 3.5, "seed": 42, "num_inference_steps": 200 } }, { "id": 3, "type": "SaveAudio", "pos": [950, 100], "size": [300, 100], "flags": {}, "order": 3, "mode": 0, "inputs": [ { "name": "audio", "type": "AUDIO", "link": 2 } ], "outputs": [], "properties": { "filename_prefix": "AudioLDM_Output" } } ], "links": [ [1, 1, 0, 2, 0, "AUDIO_LDM_MODEL"], [2, 2, 0, 3, 0, "AUDIO"] ], "groups": [], "config": {}, "extra": {}, "version": 0.4 } ``` 使用指南： 一、环境检测与准备 1. 系统要求： - Python 3.8-3.11 - PyTorch 1.13+（推荐 2.0+） - CUDA 11.8+（NVIDIA GPU 用户） - 至少 8GB 显存（推荐 12GB+） 2. 依赖安装： ```bash pip install torch torchaudio --extra-index-url https://download.pytorch.org/whl/cu118 pip install transformers diffusers accelerate ``` 3. ComfyUI 插件安装： - 将 AudioLDM 节点插件放入 Co...

存档时间线

版本索引永久保留；内容副本只保留最新 1 份，更早版本仅留索引与哈希（存档时间线的证据链不会因此断裂）。

下载存档内容副本

相关资产