Skip to content

fix: disable extra T5 mask padding for Wan #1375

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
leejet merged 1 commit into from
Mar 30, 2026
+3 −3
Merged

fix: disable extra T5 mask padding for Wan #1375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/conditioner.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1313,14 +1313,14 @@ struct T5CLIPEmbedder : public Conditioner {
std::shared_ptr<T5Runner> t5;
size_t chunk_len = 512;
bool use_mask = false;
int mask_pad = 1;
int mask_pad = 0;
bool is_umt5 = false;

T5CLIPEmbedder(ggml_backend_t backend,
bool offload_params_to_cpu,
const String2TensorStorage& tensor_storage_map = {},
bool use_mask = false,
int mask_pad = 1,
int mask_pad = 0,
bool is_umt5 = false)
: use_mask(use_mask), mask_pad(mask_pad), t5_tokenizer(is_umt5) {
bool use_t5 = false;
Expand Down
2 changes: 1 addition & 1 deletion src/stable-diffusion.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -493,7 +493,7 @@ class StableDiffusionGGML {
offload_params_to_cpu,
tensor_storage_map,
true,
1,
0,
true);
diffusion_model = std::make_shared<WanModel>(backend,
offload_params_to_cpu,
Expand Down
Loading