upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-07-31 23:30:42 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: add sd3 support (#298)

Browse Source
This commit is contained in:
leejet
2024-07-28 15:44:08 +08:00
committed by GitHub
parent 9c51d8787f
commit 73c2176648
30 changed files with 2429654 additions and 1075 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
model.cpp
View File

@@ -161,6 +161,10 @@ std::string convert_open_clip_to_hf_clip(const std::string& name) {
prefix = new_name.substr(0, new_name.size() - strlen("vision_model.visual_projection.weight"));
new_name = prefix + "visual_projection.weight";
return new_name;
} else if (ends_with(new_name, "transformer.text_projection.weight")) {
prefix = new_name.substr(0, new_name.size() - strlen("transformer.text_projection.weight"));
new_name = prefix + "transformer.text_model.text_projection";
return new_name;
} else {
return new_name;
}
@@ -420,7 +424,7 @@ std::string convert_diffusers_name_to_compvis(std::string key, char seq) {
std::string convert_tensor_name(const std::string& name) {
std::string new_name = name;
if (starts_with(name, "cond_stage_model.") || starts_with(name, "conditioner.embedders.") || ends_with(name, ".vision_model.visual_projection.weight")) {
if (starts_with(name, "cond_stage_model.") || starts_with(name, "conditioner.embedders.") || starts_with(name, "text_encoders.") || ends_with(name, ".vision_model.visual_projection.weight")) {
new_name = convert_open_clip_to_hf_clip(name);
} else if (starts_with(name, "first_stage_model.decoder")) {
new_name = convert_vae_decoder_name(name);
@@ -1288,6 +1292,9 @@ bool ModelLoader::init_from_ckpt_file(const std::string& file_path, const std::s
SDVersion ModelLoader::get_sd_version() {
TensorStorage token_embedding_weight;
for (auto& tensor_storage : tensor_storages) {
if (tensor_storage.name.find("model.diffusion_model.joint_blocks.23.") != std::string::npos) {
return VERSION_3_2B;
}
if (tensor_storage.name.find("conditioner.embedders.1") != std::string::npos) {
return VERSION_XL;
}
@@ -1323,7 +1330,8 @@ ggml_type ModelLoader::get_sd_wtype() {
}
if (tensor_storage.name.find(".weight") != std::string::npos &&
tensor_storage.name.find("time_embed") != std::string::npos) {
(tensor_storage.name.find("time_embed") != std::string::npos) ||
tensor_storage.name.find("context_embedder") != std::string::npos) {
return tensor_storage.type;
}
}
@@ -1335,6 +1343,11 @@ std::string ModelLoader::load_merges() {
return merges_utf8_str;
}
std::string ModelLoader::load_t5_tokenizer_json() {
std::string json_str(reinterpret_cast<const char*>(t5_tokenizer_json_str), sizeof(t5_tokenizer_json_str));
return json_str;
}
std::vector<TensorStorage> remove_duplicates(const std::vector<TensorStorage>& vec) {
std::vector<TensorStorage> res;
std::unordered_map<std::string, size_t> name_to_index_map;