update acestep default inference steps (#1417)

mi804 · web-flow · commit 56f58054acb8 · 2026-04-28T19:18:48.000+08:00
diff --git a/examples/ace_step/model_inference/acestep-v15-base-CoverTask.py b/examples/ace_step/model_inference/acestep-v15-base-CoverTask.py
@@ -39,7 +39,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base-cover.wav")
diff --git a/examples/ace_step/model_inference/acestep-v15-base-RepaintTask.py b/examples/ace_step/model_inference/acestep-v15-base-RepaintTask.py
@@ -40,7 +40,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 
diff --git a/examples/ace_step/model_inference/acestep-v15-base.py b/examples/ace_step/model_inference/acestep-v15-base.py
@@ -25,7 +25,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base.wav")
diff --git a/examples/ace_step/model_inference/acestep-v15-sft.py b/examples/ace_step/model_inference/acestep-v15-sft.py
@@ -32,7 +32,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-sft.wav")
diff --git a/examples/ace_step/model_inference/acestep-v15-xl-base.py b/examples/ace_step/model_inference/acestep-v15-xl-base.py
@@ -32,7 +32,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-base.wav")
diff --git a/examples/ace_step/model_inference/acestep-v15-xl-sft.py b/examples/ace_step/model_inference/acestep-v15-xl-sft.py
@@ -31,7 +31,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-sft.wav")
diff --git a/examples/ace_step/model_inference_low_vram/acestep-v15-base-CoverTask.py b/examples/ace_step/model_inference_low_vram/acestep-v15-base-CoverTask.py
@@ -51,7 +51,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base-cover.wav")
diff --git a/examples/ace_step/model_inference_low_vram/acestep-v15-base-RepaintTask.py b/examples/ace_step/model_inference_low_vram/acestep-v15-base-RepaintTask.py
@@ -52,7 +52,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 
diff --git a/examples/ace_step/model_inference_low_vram/acestep-v15-base.py b/examples/ace_step/model_inference_low_vram/acestep-v15-base.py
@@ -38,7 +38,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base-low-vram.wav")
diff --git a/examples/ace_step/model_inference_low_vram/acestep-v15-sft.py b/examples/ace_step/model_inference_low_vram/acestep-v15-sft.py
@@ -38,7 +38,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-sft-low-vram.wav")
diff --git a/examples/ace_step/model_inference_low_vram/acestep-v15-xl-base.py b/examples/ace_step/model_inference_low_vram/acestep-v15-xl-base.py
@@ -39,7 +39,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-base-low-vram.wav")
diff --git a/examples/ace_step/model_inference_low_vram/acestep-v15-xl-sft.py b/examples/ace_step/model_inference_low_vram/acestep-v15-xl-sft.py
@@ -38,7 +38,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-sft-low-vram.wav")
diff --git a/examples/ace_step/model_training/validate_full/Ace-Step1.5.py b/examples/ace_step/model_training/validate_full/Ace-Step1.5.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "Ace-Step1.5_full.wav")
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-base.py b/examples/ace_step/model_training/validate_full/acestep-v15-base.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=42,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base_full.wav")
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-sft.py b/examples/ace_step/model_training/validate_full/acestep-v15-sft.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-sft_full.wav")
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-turbo-continuous.py b/examples/ace_step/model_training/validate_full/acestep-v15-turbo-continuous.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-turbo-continuous_full.wav")
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-turbo-shift1.py b/examples/ace_step/model_training/validate_full/acestep-v15-turbo-shift1.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
     shift=1,
 )
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-turbo-shift3.py b/examples/ace_step/model_training/validate_full/acestep-v15-turbo-shift3.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-turbo-shift3_full.wav")
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-xl-base.py b/examples/ace_step/model_training/validate_full/acestep-v15-xl-base.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-base_full.wav")
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-xl-sft.py b/examples/ace_step/model_training/validate_full/acestep-v15-xl-sft.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-sft_full.wav")
diff --git a/examples/ace_step/model_training/validate_full/acestep-v15-xl-turbo.py b/examples/ace_step/model_training/validate_full/acestep-v15-xl-turbo.py
@@ -29,7 +29,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=8,
+    num_inference_steps=50,
     cfg_scale=1.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-turbo_full.wav")
diff --git a/examples/ace_step/model_training/validate_lora/Ace-Step1.5.py b/examples/ace_step/model_training/validate_lora/Ace-Step1.5.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "Ace-Step1.5_lora.wav")
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-base.py b/examples/ace_step/model_training/validate_lora/acestep-v15-base.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base_lora.wav")
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-sft.py b/examples/ace_step/model_training/validate_lora/acestep-v15-sft.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-sft_lora.wav")
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-turbo-continuous.py b/examples/ace_step/model_training/validate_lora/acestep-v15-turbo-continuous.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-turbo-continuous_lora.wav")
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-turbo-shift1.py b/examples/ace_step/model_training/validate_lora/acestep-v15-turbo-shift1.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
     shift=1,
 )
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-turbo-shift3.py b/examples/ace_step/model_training/validate_lora/acestep-v15-turbo-shift3.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-turbo-shift3_lora.wav")
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-xl-base.py b/examples/ace_step/model_training/validate_lora/acestep-v15-xl-base.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-base_lora.wav")
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-xl-sft.py b/examples/ace_step/model_training/validate_lora/acestep-v15-xl-sft.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-sft_lora.wav")
diff --git a/examples/ace_step/model_training/validate_lora/acestep-v15-xl-turbo.py b/examples/ace_step/model_training/validate_lora/acestep-v15-xl-turbo.py
@@ -27,7 +27,7 @@
     timesignature="4",
     vocal_language="zh",
     seed=1,
-    num_inference_steps=30,
+    num_inference_steps=50,
     cfg_scale=4.0,
 )
 save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-turbo_lora.wav")

Original file line number	Diff line number	Diff line change
`@@ -39,7 +39,7 @@`
`39`	`39`	`timesignature="4",`
`40`	`40`	`vocal_language="zh",`
`41`	`41`	`seed=42,`
`42`		`- num_inference_steps=30,`
	`42`	`+ num_inference_steps=50,`
`43`	`43`	`cfg_scale=4.0,`
`44`	`44`	`)`
`45`	`45`	`save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base-cover.wav")`
Original file line number	Diff line number	Diff line change
`@@ -40,7 +40,7 @@`
`40`	`40`	`timesignature="4",`
`41`	`41`	`vocal_language="zh",`
`42`	`42`	`seed=1,`
`43`		`- num_inference_steps=30,`
	`43`	`+ num_inference_steps=50,`
`44`	`44`	`cfg_scale=4.0,`
`45`	`45`	`)`
`46`	`46`
Original file line number	Diff line number	Diff line change
`@@ -25,7 +25,7 @@`
`25`	`25`	`timesignature="4",`
`26`	`26`	`vocal_language="zh",`
`27`	`27`	`seed=42,`
`28`		`- num_inference_steps=30,`
	`28`	`+ num_inference_steps=50,`
`29`	`29`	`cfg_scale=4.0,`
`30`	`30`	`)`
`31`	`31`	`save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base.wav")`
Original file line number	Diff line number	Diff line change
`@@ -32,7 +32,7 @@`
`32`	`32`	`timesignature="4",`
`33`	`33`	`vocal_language="zh",`
`34`	`34`	`seed=42,`
`35`		`- num_inference_steps=30,`
	`35`	`+ num_inference_steps=50,`
`36`	`36`	`cfg_scale=4.0,`
`37`	`37`	`)`
`38`	`38`	`save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-sft.wav")`
Original file line number	Diff line number	Diff line change
`@@ -31,7 +31,7 @@`
`31`	`31`	`timesignature="4",`
`32`	`32`	`vocal_language="zh",`
`33`	`33`	`seed=42,`
`34`		`- num_inference_steps=30,`
	`34`	`+ num_inference_steps=50,`
`35`	`35`	`cfg_scale=4.0,`
`36`	`36`	`)`
`37`	`37`	`save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-xl-sft.wav")`
Original file line number	Diff line number	Diff line change
`@@ -51,7 +51,7 @@`
`51`	`51`	`timesignature="4",`
`52`	`52`	`vocal_language="zh",`
`53`	`53`	`seed=42,`
`54`		`- num_inference_steps=30,`
	`54`	`+ num_inference_steps=50,`
`55`	`55`	`cfg_scale=4.0,`
`56`	`56`	`)`
`57`	`57`	`save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base-cover.wav")`
Original file line number	Diff line number	Diff line change
`@@ -52,7 +52,7 @@`
`52`	`52`	`timesignature="4",`
`53`	`53`	`vocal_language="zh",`
`54`	`54`	`seed=1,`
`55`		`- num_inference_steps=30,`
	`55`	`+ num_inference_steps=50,`
`56`	`56`	`cfg_scale=4.0,`
`57`	`57`	`)`
`58`	`58`
Original file line number	Diff line number	Diff line change
`@@ -38,7 +38,7 @@`
`38`	`38`	`timesignature="4",`
`39`	`39`	`vocal_language="zh",`
`40`	`40`	`seed=42,`
`41`		`- num_inference_steps=30,`
	`41`	`+ num_inference_steps=50,`
`42`	`42`	`cfg_scale=4.0,`
`43`	`43`	`)`
`44`	`44`	`save_audio(audio, pipe.vae.sampling_rate, "acestep-v15-base-low-vram.wav")`