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

update wan2.2-S2V training

Browse Source
This commit is contained in:
lzws
2025-10-21 19:59:44 +08:00
parent b168d7aa8b
commit 30292d9411
5 changed files with 7 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
diffsynth/pipelines/wan_video_new.py
View File

@@ -1028,8 +1028,8 @@ class WanVideoUnit_S2V(PipelineUnit):
if (inputs_shared.get("input_audio") is None and inputs_shared.get("audio_embeds") is None) or pipe.audio_encoder is None or pipe.audio_processor is None:
return inputs_shared, inputs_posi, inputs_nega
num_frames, height, width, tiled, tile_size, tile_stride = inputs_shared.get("num_frames"), inputs_shared.get("height"), inputs_shared.get("width"), inputs_shared.get("tiled"), inputs_shared.get("tile_size"), inputs_shared.get("tile_stride")
input_audio, audio_embeds, audio_sample_rate = inputs_shared.pop("input_audio"), inputs_shared.pop("audio_embeds"), inputs_shared.get("audio_sample_rate")
s2v_pose_video, s2v_pose_latents, motion_video = inputs_shared.pop("s2v_pose_video"), inputs_shared.pop("s2v_pose_latents"), inputs_shared.pop("motion_video")
input_audio, audio_embeds, audio_sample_rate = inputs_shared.pop("input_audio", None), inputs_shared.pop("audio_embeds", None), inputs_shared.get("audio_sample_rate", 16000)
s2v_pose_video, s2v_pose_latents, motion_video = inputs_shared.pop("s2v_pose_video", None), inputs_shared.pop("s2v_pose_latents", None), inputs_shared.pop("motion_video", None)
audio_input_positive = self.process_audio(pipe, input_audio, audio_sample_rate, num_frames, audio_embeds=audio_embeds)
inputs_posi.update(audio_input_positive)

2
diffsynth/trainers/unified_dataset.py
View File

@@ -231,7 +231,7 @@ class LoadAudio(DataProcessingOperator):
def __call__(self, data: str):
import librosa
input_audio, sample_rate = librosa.load(data, sr=self.sr)
return {'input_audio':input_audio, 'sample_rate':sample_rate}
return input_audio
class UnifiedDataset(torch.utils.data.Dataset):