theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-22 16:50:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

[feature]:Add adaptation of all models to zero3

Browse Source
This commit is contained in:
feng0w0
2026-01-31 16:50:18 +08:00
parent 3140199c96
commit 2070bbd925
6 changed files with 58 additions and 144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
diffsynth/models/wan_video_vace.py
View File

@@ -1,6 +1,6 @@
import torch
from .wan_video_dit import DiTBlock
from ..core.gradient import gradient_checkpoint_forward
class VaceWanAttentionBlock(DiTBlock):
def __init__(self, has_image_input, dim, num_heads, ffn_dim, eps=1e-6, block_id=0):
@@ -62,26 +62,13 @@ class VaceWanModel(torch.nn.Module):
dim=1) for u in c
])
def create_custom_forward(module):
def custom_forward(*inputs):
return module(*inputs)
return custom_forward
for block in self.vace_blocks:
if use_gradient_checkpointing_offload:
with torch.autograd.graph.save_on_cpu():
c = torch.utils.checkpoint.checkpoint(
create_custom_forward(block),
c, x, context, t_mod, freqs,
use_reentrant=False,
)
elif use_gradient_checkpointing:
c = torch.utils.checkpoint.checkpoint(
create_custom_forward(block),
c, x, context, t_mod, freqs,
use_reentrant=False,
)
else:
c = block(c, x, context, t_mod, freqs)
c = gradient_checkpoint_forward(
block,
use_gradient_checkpointing,
use_gradient_checkpointing_offload,
c, x, context, t_mod, freqs
)
hints = torch.unbind(c)[:-1]
return hints