"The model is released under the Apache-2.0 license and is free for commercial use. It also has good inference speed: the model synthesizes up to 4 minutes of music in just 20 seconds on an A100 GPU."
hmmm wonder if it works on 3090/ 4090, not sure many of us have a spare a100 lol
EDIT: works ok on a 3090, VERY fast. low quality audio but does do music and lyrics. VERY interesting! Will be keen to see where this goes, maybe next year I wont need my annual suno subscription.
I too am poking around. Can run this on 3060 12gb variant. average 1.98it/s. Music Quality is garbled low quality. Good Vocal Creation. Lowering Value of Vocals increases Music Quality. However Lyrics go completely out the window. (Note this is after 10 mins of playing). This plus a couple of other apache 2 projects for creating and modifying vocals and you could create something interesting. Modifying the SD Shift down to 2 seems to work upon occasion for clearing up a sound. ive also found turning the scheduler to kl_optimal can give a cleaner sound.....
the workflow (ace_step_1_t2m.json) without changing all parameters produces weird music that sounds overlapped by several music. My machine is Macbook Pro M4.
"The model is released under the Apache-2.0 license and is free for commercial use. It also has good inference speed: the model synthesizes up to 4 minutes of music in just 20 seconds on an A100 GPU."
hmmm wonder if it works on 3090/ 4090, not sure many of us have a spare a100 lol
EDIT: works ok on a 3090, VERY fast. low quality audio but does do music and lyrics. VERY interesting! Will be keen to see where this goes, maybe next year I wont need my annual suno subscription.
I too am poking around. Can run this on 3060 12gb variant. average 1.98it/s. Music Quality is garbled low quality. Good Vocal Creation. Lowering Value of Vocals increases Music Quality. However Lyrics go completely out the window. (Note this is after 10 mins of playing). This plus a couple of other apache 2 projects for creating and modifying vocals and you could create something interesting. Modifying the SD Shift down to 2 seems to work upon occasion for clearing up a sound. ive also found turning the scheduler to kl_optimal can give a cleaner sound.....
interesting to know what other think
the workflow (ace_step_1_t2m.json) without changing all parameters produces weird music that sounds overlapped by several music. My machine is Macbook Pro M4.
it seems the quality is on a absolute low level. not possible to use it in a commercial
The docs contain missing files
https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/audio/ace-stepace_step_1_m2m_editing.json
goes to 404.
Cmon guys, how you mess your own documentation?
Fixed
You are really bad at this.
No, its not fixed... the first link works, but the
ACE-Step ComfyUI Audio-to-Audio Workflow
does not.
https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/audio/ace-stepace_step_1_m2m_editing.json
just wow...404 again
Do you need help little buddy?
I know why now, there's a missing "/" on the link you sent. Where did you get the links? I can't find it anywhere. https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/audio/ace-step/ace_step_1_m2m_editing.json
ACEstep has definitely brought out my inner 13 year old...I've been having the best time with this today.
ACE-Step在comfyui示例中生成的中文歌曲音质和ACE-Step官方一键包本地运行的音质对比，音质会比comfyui示例生成的效果好，貌似少了很多配置文件和功能，请问能否修复完善呢
最近有做了一个更新改善的版本 https://comfyanonymous.github.io/ComfyUI_examples/audio/