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

support ltx2 two stage pipeline & vram

Browse Source
This commit is contained in:
mi804
2026-01-30 16:55:40 +08:00
parent b1a2782ad7
commit 4f23caa55f
7 changed files with 227 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
diffsynth/configs/vram_management_module_maps.py
View File

@@ -210,4 +210,37 @@ VRAM_MANAGEMENT_MODULE_MAPS = {
"torch.nn.LayerNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
},
"diffsynth.models.ltx2_dit.LTXModel": {
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
"torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.ltx2_upsampler.LTX2LatentUpsampler": {
"torch.nn.Conv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.Conv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.GroupNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.ltx2_video_vae.LTX2VideoEncoder": {
"torch.nn.Conv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.ltx2_video_vae.LTX2VideoDecoder": {
"torch.nn.Conv3d": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.ltx2_audio_vae.LTX2AudioDecoder": {
"torch.nn.Conv2d": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.ltx2_audio_vae.LTX2Vocoder": {
"torch.nn.Conv1d": "diffsynth.core.vram.layers.AutoWrappedModule",
"torch.nn.ConvTranspose1d": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.ltx2_text_encoder.LTX2TextEncoderPostModules": {
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
"torch.nn.RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"diffsynth.models.ltx2_text_encoder.Embeddings1DConnector": "diffsynth.core.vram.layers.AutoWrappedModule",
},
"diffsynth.models.ltx2_text_encoder.LTX2TextEncoder": {
"torch.nn.Linear": "diffsynth.core.vram.layers.AutoWrappedLinear",
"transformers.models.gemma3.modeling_gemma3.Gemma3MultiModalProjector": "diffsynth.core.vram.layers.AutoWrappedModule",
"transformers.models.gemma3.modeling_gemma3.Gemma3RMSNorm": "diffsynth.core.vram.layers.AutoWrappedModule",
"transformers.models.gemma3.modeling_gemma3.Gemma3TextScaledWordEmbedding": "diffsynth.core.vram.layers.AutoWrappedModule",
},
}