Instructions to use ntc-ai/minimax-music3-concept-sliders with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ntc-ai/minimax-music3-concept-sliders with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-Music-3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ntc-ai/minimax-music3-concept-sliders") prompt = "Same prompt and lyrics. Energy slider Off then Loud +1. Unidirectional lyric-hold LM." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Add ComfyUI siblings for uni v24 sliders (untested)
Browse files
weights/joy-lm-v24-uni/joy-lm-v24-uni_last_comfyui.safetensors.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"arch": "music3_lm",
|
| 3 |
+
"fused_qkv": false,
|
| 4 |
+
"host": "lm",
|
| 5 |
+
"unit_scale": true,
|
| 6 |
+
"recommended_range": [
|
| 7 |
+
0.5,
|
| 8 |
+
1.5
|
| 9 |
+
],
|
| 10 |
+
"n_keys": 432
|
| 11 |
+
}
|