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

ltx iclora train

Browse Source
This commit is contained in:
mi804
2026-02-27 18:43:53 +08:00
parent 5996c2b068
commit 8b9a094c1b
7 changed files with 271 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
diffsynth/diffusion/base_pipeline.py
View File

@@ -94,20 +94,23 @@ class BasePipeline(torch.nn.Module):
return self
def check_resize_height_width(self, height, width, num_frames=None):
def check_resize_height_width(self, height, width, num_frames=None, verbose=1):
# Shape check
if height % self.height_division_factor != 0:
height = (height + self.height_division_factor - 1) // self.height_division_factor * self.height_division_factor
print(f"height % {self.height_division_factor} != 0. We round it up to {height}.")
if verbose > 0:
print(f"height % {self.height_division_factor} != 0. We round it up to {height}.")
if width % self.width_division_factor != 0:
width = (width + self.width_division_factor - 1) // self.width_division_factor * self.width_division_factor
print(f"width % {self.width_division_factor} != 0. We round it up to {width}.")
if verbose > 0:
print(f"width % {self.width_division_factor} != 0. We round it up to {width}.")
if num_frames is None:
return height, width
else:
if num_frames % self.time_division_factor != self.time_division_remainder:
num_frames = (num_frames + self.time_division_factor - 1) // self.time_division_factor * self.time_division_factor + self.time_division_remainder
print(f"num_frames % {self.time_division_factor} != {self.time_division_remainder}. We round it up to {num_frames}.")
if verbose > 0:
print(f"num_frames % {self.time_division_factor} != {self.time_division_remainder}. We round it up to {num_frames}.")
return height, width, num_frames

2
diffsynth/pipelines/ltx2_audio_video.py
View File

@@ -565,7 +565,7 @@ class LTX2AudioVideoUnit_InContextVideoEmbedder(PipelineUnit):
expected_height = height // in_context_downsample_factor // 2 if use_two_stage_pipeline else height // in_context_downsample_factor
expected_width = width // in_context_downsample_factor // 2 if use_two_stage_pipeline else width // in_context_downsample_factor
current_h, current_w, current_f = in_context_video[0].size[1], in_context_video[0].size[0], len(in_context_video)
h, w, f = pipe.check_resize_height_width(expected_height, expected_width, current_f)
h, w, f = pipe.check_resize_height_width(expected_height, expected_width, current_f, verbose=0)
if current_h != h or current_w != w:
in_context_video = [img.resize((w, h)) for img in in_context_video]
if current_f != f: