You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: tutorials/audio/ace-step/ace-step-v1-5.mdx
+7-7Lines changed: 7 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -96,28 +96,28 @@ The split version allows you to download individual model components separately.
96
96
│ └── ace_1.5_vae.safetensors
97
97
```
98
98
99
-
## Key Features
99
+
## ACE-Step 1.5 Key Features in ComfyUI
100
100
101
101
### Chain-of-Thought Planning
102
102
103
-
The model synthesizes metadata, lyrics, and captions via Chain-of-Thought reasoning to guide the diffusion process, resulting in more coherent long-form compositions.
103
+
The ACE-Step 1.5 model synthesizes metadata, lyrics, and captions via Chain-of-Thought reasoning to guide the diffusion process, resulting in more coherent long-form compositions.
104
104
105
105
### Hybrid LM + DiT Architecture
106
106
107
-
ACE-Step 1.5 combines a Language Model that plans the song structure with a Diffusion Transformer (DiT) that handles audio synthesis.
107
+
ACE-Step 1.5 combines a Language Model that plans the song structure with a Diffusion Transformer (DiT) that handles audio synthesis, all running natively in ComfyUI.
108
108
109
-
### LoRA Fine-Tuning
109
+
### LoRA Fine-Tuning in ComfyUI
110
110
111
-
With just a few songs, you can train a LoRA that captures a specific style. Because you run it locally, you own the LoRA and don't have to worry about data leakage.
111
+
With just a few songs, you can train a LoRA that captures a specific style. Because you run ACE-Step 1.5 locally in ComfyUI, you own the LoRA and don't have to worry about data leakage.
112
112
113
-
## Coming Soon
113
+
## Coming Soon to ComfyUI
114
114
115
115
These features are available in ACE-Step 1.5 but not yet supported in ComfyUI:
116
116
117
117
-**Cover**: Give the model any song as input along with a new prompt and lyrics, and it will reimagine the track in a completely different style
118
118
-**Repaint**: Select a segment, regenerate just that section, and the model stitches it back in while keeping everything else untouched
0 commit comments