ace gguf
by calcuis
Open source · 983 downloads · 29 likes
1.8
(29 reviews)AudioAPI & LocalAbout
The ACE GGUF model is an optimized and quantized version of the ACE-Step model, specifically designed to work with ComfyUI. It integrates an encoder, a VAE, and the base model into a GGUF format, enabling immediate use without complex configuration. This model stands out for its lightweight nature and fast loading speed while maintaining high performance through optimized management of key tensors. It is particularly well-suited for audio generation and voice synthesis, offering an efficient alternative to traditional safetensors versions. ACE GGUF is ideal for users looking to leverage high-performance audio models in environments like ComfyUI, with simplified integration and reduced resource usage.
Documentation
gguf quantized ace-step-v1-3.5b
- base model from ace-step
- full set gguf (model+encoder+vae) works right away
setup (once)
- drag ace-step to >
./ComfyUI/models/diffusion_models - drag umt5-base to >
./ComfyUI/models/text_encoders - drag pig to >
./ComfyUI/models/vae
workflow
- drag json or demo audio below to browser for workflow
| Prompt | Audio Sample |
|---|---|
female singing pop music electronic beats fennec corecute fennec girlmassive fennec earsbig fluffy taillong blonde wavy hairlarge blue eyesI love fennec girl | 🎧 ace-step |
female singing pop music electronic beats fennec corecute pinky pigmassive pinky earsbig fluffy taillong cutie wavy hairlarge blue eyesI love pinky pig | 🎧 ace-audio |
review
- note: as need to keep some key tensors (in f32 status) to make it works; file size might not decrease that much; but load faster than safetensors checkpoint in general (no last minute bottle neck problem)
- rebuilding umt5-base tokenizer logic applied successfully; upgrade your node to the latest version for umt5-base encoder support; hence, safetensors checkpoint is no longer needed (removed here; if you want it still, you could get it from comfyui-org)
- get more umt5-base encoder here
bonus: fp8/16/32 scaled stable-audio-open-1.0 with gguf quantized t5_base encoder
- base model from stabilityai
- note: this is a different model; don't mix it up; also powerful and lite weight
setup (once)
- drag t5-base to >
./ComfyUI/models/text_encoders - drag safetensors to >
./ComfyUI/models/checkpoints - drag pig to >
./ComfyUI/models/vae
| Prompt | Audio Sample |
|---|---|
| heaven church electronic dance music | 🎧 stable-audio |
review
- note: the safetensors checkpoint in this repo is an extracted version; only contains model and condition switch tensors (extremely lite weighted); no clip and vae inside; should use it along with separate clip (text encoder) and vae
- opt to get fp8/16/32 scaled checkpoint with model and vae embedded here
- get more t5-base encoder here
reference
- comfyui from comfyanonymous
- pig architecture from connector
- gguf-node (pypi|repo|pack)
Capabilities & Tags
ggufgguf-nodetext-to-audio
Links & Resources