Update README.md

README.md

@@ -10,7 +10,7 @@ tags:
 - base model from [ace-step](https://huggingface.co/ACE-Step)
 - full set gguf (model+encoder+vae) works right away
 - 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
-- rebuilding umt5-base tokenizer logic applied successfully (credit should give to city96); upgrade your node to the latest version for umt5-base encoder support; hence, safetensors checkpoint is no longer needed
+- rebuilding umt5-base tokenizer logic applied successfully (similar to umt5-xxl; credit should give to city96); upgrade your node to the latest version for umt5-base encoder support; hence, safetensors checkpoint is no longer needed
 
 ### **setup (once)**
 - drag **ace-step** to > `./ComfyUI/models/diffusion_models`
@@ -21,7 +21,7 @@ tags:
 
 ## extra/bonus: fp8/16/32 scaled stable-audio-open-1.0 with gguf quantized t5_base encoder
 - base model from [stabilityai](https://huggingface.co/stabilityai/stable-audio-open-1.0)
-- note: this is a different model from ace-step above; don't mix it up
+- note: this is a different model; don't mix it up; also powerful and lite weight
 - dry running
 
 ### **setup (once)**