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

Mova (#1337)

Browse Source 
* support mova inference

* mova media_io

* add unified audio_video api & fix bug of mono audio input for ltx

* support mova train

* mova docs

* fix bug
This commit is contained in:
Hong Zhang
2026-03-13 13:06:07 +08:00
committed by GitHub
parent 4741542523
commit 681df93a85
37 changed files with 3102 additions and 181 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
diffsynth/configs/vram_management_module_maps.py
View File

@@ -249,6 +249,24 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
"torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.Embedding": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.mova_audio_dit.MovaAudioDit": {
"diffsynth.models.wan_video_dit.DiTBlock": "diffsynth.core.vram.layers.AutoWrappedNonRecurseModule",
"diffsynth.models.wan_video_dit.Head": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
"torch.nn.Conv1d": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"diffsynth.models.wan_video_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.mova_dual_tower_bridge.DualTowerConditionalBridge": {
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
"torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"diffsynth.models.wan_video_dit.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.mova_audio_vae.DacVAE": {
"diffsynth.models.mova_audio_vae.Snake1d": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.Conv1d": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.ConvTranspose1d": "diffsynth.core.vram.layers.AutoWrappedModule",
},
}
def QwenImageTextEncoder_Module_Map_Updater():