feat: add PhotoMaker Version 2 support (#358)

* first attempt at updating to photomaker v2

* continue adding photomaker v2 modules

* finishing the last few pieces for photomaker v2; id_embeds need to be done by a manual step and pass as an input file

* added a name converter for Photomaker V2; build ok

* more debugging underway

* failing at cuda mat_mul

* updated chunk_half to be more efficient; redo feedforward

* fixed a bug: carefully using ggml_view_4d to get chunks of a tensor; strides need to be recalculated or set properly; still failing at soft_max cuda op

* redo weight calculation and weight*v

* fixed a bug now Photomaker V2 kinds of working

* add python script for face detection (Photomaker V2 needs)

* updated readme for photomaker

* fixed a bug causing PMV1 crashing; both V1 and V2 work

* fixed clean_input_ids for PMV2

* fixed a double counting bug in tokenize_with_trigger_token

* updated photomaker readme

* removed some commented code

* improved reconstructing class word free prompt

* changed reading id_embed to raw binary using existing load tensor function; this is more efficient than using model load and also makes it easier to work with sd server

* minor clean up

---------

Co-authored-by: bssrdf <bssrdf@gmail.com>

util.cpp

@@ -276,6 +276,24 @@ std::string path_join(const std::string& p1, const std::string& p2) {
     return p1 + "/" + p2;
 }
 
+std::vector<std::string> splitString(const std::string& str, char delimiter) {
+    std::vector<std::string> result;
+    size_t start = 0;
+    size_t end = str.find(delimiter);
+
+    while (end != std::string::npos) {
+        result.push_back(str.substr(start, end - start));
+        start = end + 1;
+        end = str.find(delimiter, start);
+    }
+
+    // Add the last segment after the last delimiter
+    result.push_back(str.substr(start));
+
+    return result;
+}
+
+
 sd_image_t* preprocess_id_image(sd_image_t* img) {
     int shortest_edge   = 224;
     int size            = shortest_edge;