theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor ltx2 stage2 pipeline (#1341)

Browse Source 
* refactor ltx2 pipeline

* fix bug
This commit is contained in:
Hong Zhang
2026-03-10 13:55:40 +08:00
committed by GitHub
parent b272253956
commit d9228074bd
5 changed files with 139 additions and 134 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py
View File

@@ -45,7 +45,6 @@ video, audio = pipe(
input_images=[image],
input_images_indexes=[0],
input_images_strength=1.0,
num_inference_steps=40,
)
write_video_audio_ltx2(
video=video,

1
examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py
View File

@@ -57,7 +57,6 @@ video, audio = pipe(
num_frames=num_frames,
tiled=True,
use_two_stage_pipeline=True,
num_inference_steps=40,
input_images=[image],
input_images_indexes=[0],
input_images_strength=1.0,

1
examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py
View File

@@ -46,7 +46,6 @@ video, audio = pipe(
input_images=[image],
input_images_indexes=[0],
input_images_strength=1.0,
num_inference_steps=40,
)
write_video_audio_ltx2(
video=video,

1
examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py
View File

@@ -58,7 +58,6 @@ video, audio = pipe(
num_frames=num_frames,
tiled=True,
use_two_stage_pipeline=True,
num_inference_steps=40,
input_images=[image],
input_images_indexes=[0],
input_images_strength=1.0,