theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-21 16:18:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

support ltx-2 t2v and i2v

Browse Source
This commit is contained in:
mi804
2026-02-02 19:53:07 +08:00
parent 1c8a0f8317
commit f4f991d409
20 changed files with 1084 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
diffsynth/models/ltx2_dit.py
View File

@@ -1442,6 +1442,10 @@ class LTXModel(torch.nn.Module):
return vx, ax
def forward(self, video_latents, video_positions, video_context, video_timesteps, audio_latents, audio_positions, audio_context, audio_timesteps):
cross_pe_max_pos = None
if self.model_type.is_video_enabled() and self.model_type.is_audio_enabled():
cross_pe_max_pos = max(self.positional_embedding_max_pos[0], self.audio_positional_embedding_max_pos[0])
self._init_preprocessors(cross_pe_max_pos)
video = Modality(video_latents, video_timesteps, video_positions, video_context)
audio = Modality(audio_latents, audio_timesteps, audio_positions, audio_context)
vx, ax = self._forward(video=video, audio=audio, perturbations=None)