upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-10-03 19:37:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: add Wan2.2 S2V (audio+img-to-video) support (#1925)

Browse Source 
Co-authored-by: leejet <leejet714@gmail.com>
This commit is contained in:
George
2026-09-13 23:33:50 +08:00
committed by GitHub
co-authored by leejet
parent 4a7da26b73
commit 0bd72f075a
32 changed files with 1533 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/pipeline/model_builders.cpp
+11
View File
@@ -8,6 +8,7 @@
#include "core/util.h"
#include "extensions/generation_extension.h"
#include "model/adapter/ip_adapter.hpp"
#include "model/audio/wav2vec2.hpp"
#include "model/diffusion/anima.hpp"
#include "model/diffusion/boogu.hpp"
#include "model/diffusion/control.hpp"
@@ -234,6 +235,16 @@ namespace sd::model_builders {
tensor_storage_map,
weight_manager);
}
if (version == VERSION_WAN2_2_S2V &&
tensor_storage_map.count("wav2vec2.encoder.layer_norm.bias") > 0) {
if (!ensure_backend_pair(ctx.backends, SDBackendModule::AUDIO_ENCODER)) {
return false;
}
result.audio_encoder = std::make_shared<Wav2Vec2::Wav2Vec2ModelRunner>(ctx.backends.runtime_backend(SDBackendModule::AUDIO_ENCODER),
tensor_storage_map,
"wav2vec2.",
weight_manager);
}
} else if (sd_version_is_lingbot_video(version)) {
bool enable_vision = false;
for (const auto& [name, _] : tensor_storage_map) {