DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add P-H3-Image generation and editing support (#2272)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-11-04 23:24:51 +08:00
1 parent 984eb0686c
commit 3e92bf990a
18 files changed
+421 -41
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/model_loader.cpp
+19
View File
@@ -578,6 +578,25 @@ SDVersion ModelLoader::get_sd_version() const {
}
if (tensor_storage.name.find("model.diffusion_model.video_patch_proj.weight") != std::string::npos &&
tensor_storage_map.find("model.diffusion_model.audio_patch_proj.weight") != tensor_storage_map.end()) {
// P-H3 uses the same DiT architecture as H3; its VAE or connector identifies the image pipeline.
auto decoder = tensor_storage_map.find("first_stage_model.decoder.proj_out.weight");
if (decoder == tensor_storage_map.end()) {
decoder = tensor_storage_map.find("vae.decoder.proj_out.weight");
}
if (decoder != tensor_storage_map.end() && decoder->second.ne[1] == 768) {
return VERSION_P_H3_IMAGE;
}
for (const std::string prefix : {"", "embeddings_connectors."}) {
if (tensor_storage_map.count(prefix + "text_encoders.ph3_image_connector.proj.weight") ||
tensor_storage_map.count(prefix + "text_encoders.llm.text_connector.proj.weight")) {
return VERSION_P_H3_IMAGE;
}
}
auto connector = tensor_storage_map.find("embeddings_connectors.proj.weight");
if (connector != tensor_storage_map.end() && connector->second.ne[0] == 12800 &&
connector->second.ne[1] == 5120 && tensor_storage_map.count("embeddings_connectors.sink_embedding")) {
return VERSION_P_H3_IMAGE;
}
return VERSION_MINIMAX_H3;
}
if (name == "model.diffusion_model.y_embedder.layer_pool.weight" &&