add support for diffusers format lora

Author: leejet

name_conversion.cpp

@@ -615,6 +615,44 @@ std::string convert_diffusers_dit_to_original_flux(std::string name) {
     return name;
 }
 
+std::string convert_diffusers_dit_to_original_lumina2(std::string name) {
+    int num_layers         = 30;
+    int num_refiner_layers = 2;
+    static std::unordered_map<std::string, std::string> z_image_name_map;
+
+    if (z_image_name_map.empty()) {
+        z_image_name_map["all_x_embedder.2-1."]  = "x_embedder.";
+        z_image_name_map["all_final_layer.2-1."] = "final_layer.";
+
+        // --- transformer blocks ---
+        auto add_attention_map = [&](const std::string& prefix, int num) {
+            for (int i = 0; i < num; ++i) {
+                std::string block_prefix = prefix + std::to_string(i) + ".";
+                std::string dst_prefix   = prefix + std::to_string(i) + ".";
+
+                z_image_name_map[block_prefix + "attention.norm_q."]   = dst_prefix + "attention.q_norm.";
+                z_image_name_map[block_prefix + "attention.norm_k."]   = dst_prefix + "attention.k_norm.";
+                z_image_name_map[block_prefix + "attention.to_out.0."] = dst_prefix + "attention.out.";
+
+                z_image_name_map[block_prefix + "attention.to_q.weight"] = dst_prefix + "attention.qkv.weight";
+                z_image_name_map[block_prefix + "attention.to_q.bias"]   = dst_prefix + "attention.qkv.bias";
+                z_image_name_map[block_prefix + "attention.to_k.weight"] = dst_prefix + "attention.qkv.weight.1";
+                z_image_name_map[block_prefix + "attention.to_k.bias"]   = dst_prefix + "attention.qkv.bias.1";
+                z_image_name_map[block_prefix + "attention.to_v.weight"] = dst_prefix + "attention.qkv.weight.2";
+                z_image_name_map[block_prefix + "attention.to_v.bias"]   = dst_prefix + "attention.qkv.bias.2";
+            }
+        };
+
+        add_attention_map("noise_refiner.", num_refiner_layers);
+        add_attention_map("context_refiner.", num_refiner_layers);
+        add_attention_map("layers.", num_layers);
+    }
+
+    replace_with_prefix_map(name, z_image_name_map);
+
+    return name;
+}
+
 std::string convert_diffusion_model_name(std::string name, std::string prefix, SDVersion version) {
     if (sd_version_is_sd1(version) || sd_version_is_sd2(version)) {
         name = convert_diffusers_unet_to_original_sd1(name);
@@ -624,6 +662,8 @@ std::string convert_diffusion_model_name(std::string name, std::string prefix, S
         name = convert_diffusers_dit_to_original_sd3(name);
     } else if (sd_version_is_flux(version) || sd_version_is_flux2(version)) {
         name = convert_diffusers_dit_to_original_flux(name);
+    } else if (sd_version_is_z_image(version)) {
+        name = convert_diffusers_dit_to_original_lumina2(name);
     }
     return name;
 }