feat: do not convert tensor names by default in convert mode (#1122)

Author: leejet

examples/cli/README.md

@@ -9,6 +9,7 @@ CLI Options:
   --preview-interval <int>    interval in denoising steps between consecutive updates of the image preview file (default is 1, meaning updating at
                               every step)
   --canny                     apply canny preprocessor (edge detection)
+  --convert-name              convert tensor name (for convert mode)
   -v, --verbose               print extra info
   --color                     colors the logging tags according to level
   --taesd-preview-only        prevents usage of taesd for decoding the final image. (for use with --preview tae)

examples/cli/main.cpp

@@ -32,6 +32,7 @@ struct SDCliParams {
 
     bool verbose          = false;
     bool canny_preprocess = false;
+    bool convert_name     = false;
 
     preview_t preview_method = PREVIEW_NONE;
     int preview_interval     = 1;
@@ -69,6 +70,10 @@ struct SDCliParams {
              "--canny",
              "apply canny preprocessor (edge detection)",
              true, &canny_preprocess},
+            {"",
+             "--convert-name",
+             "convert tensor name (for convert mode)",
+             true, &canny_preprocess},
             {"-v",
              "--verbose",
              "print extra info",
@@ -174,6 +179,7 @@ struct SDCliParams {
             << "  verbose: " << (verbose ? "true" : "false") << ",\n"
             << "  color: " << (color ? "true" : "false") << ",\n"
             << "  canny_preprocess: " << (canny_preprocess ? "true" : "false") << ",\n"
+            << "  convert_name: " << (convert_name ? "true" : "false") << ",\n"
             << "  preview_method: " << previews_str[preview_method] << ",\n"
             << "  preview_interval: " << preview_interval << ",\n"
             << "  preview_path: \"" << preview_path << "\",\n"
@@ -387,7 +393,8 @@ int main(int argc, const char* argv[]) {
                                ctx_params.vae_path.c_str(),
                                cli_params.output_path.c_str(),
                                ctx_params.wtype,
-                               ctx_params.tensor_type_rules.c_str());
+                               ctx_params.tensor_type_rules.c_str(),
+                               cli_params.convert_name);
         if (!success) {
             LOG_ERROR("convert '%s'/'%s' to '%s' failed",
                       ctx_params.model_path.c_str(),

model.cpp

@@ -1783,7 +1783,12 @@ int64_t ModelLoader::get_params_mem_size(ggml_backend_t backend, ggml_type type)
     return mem_size;
 }
 
-bool convert(const char* input_path, const char* vae_path, const char* output_path, sd_type_t output_type, const char* tensor_type_rules) {
+bool convert(const char* input_path,
+             const char* vae_path,
+             const char* output_path,
+             sd_type_t output_type,
+             const char* tensor_type_rules,
+             bool convert_name) {
     ModelLoader model_loader;
 
     if (!model_loader.init_from_file(input_path)) {
@@ -1797,7 +1802,9 @@ bool convert(const char* input_path, const char* vae_path, const char* output_pa
             return false;
         }
     }
-    model_loader.convert_tensors_name();
+    if (convert_name) {
+        model_loader.convert_tensors_name();
+    }
     bool success = model_loader.save_to_gguf_file(output_path, (ggml_type)output_type, tensor_type_rules);
     return success;
 }

stable-diffusion.h

@@ -365,7 +365,8 @@ SD_API bool convert(const char* input_path,
                     const char* vae_path,
                     const char* output_path,
                     enum sd_type_t output_type,
-                    const char* tensor_type_rules);
+                    const char* tensor_type_rules,
+                    bool convert_name);
 
 SD_API bool preprocess_canny(sd_image_t image,
                              float high_threshold,