From fdd4ff827e8de678c94612b78c87b1039d5a9592 Mon Sep 17 00:00:00 2001
From: henrisel <henri.sellis@ut.ee>
Date: Mon, 10 Nov 2025 18:19:16 +0200
Subject: [PATCH] reimplement function from invokeai_mcp_server to make
 requests to local InvokeAI

---
 3d-generation-pipeline/invoke_ai_api.py       | 72 +++++++++++++++++++
 .../_PROJECT/Scenes/DeltaBuilding_base.unity  |  4 +-
 .../ModelGenerationPipelineStarter.cs         |  4 +-
 3 files changed, 77 insertions(+), 3 deletions(-)
 create mode 100644 3d-generation-pipeline/invoke_ai_api.py

diff --git a/3d-generation-pipeline/invoke_ai_api.py b/3d-generation-pipeline/invoke_ai_api.py
new file mode 100644
index 00000000..630400a8
--- /dev/null
+++ b/3d-generation-pipeline/invoke_ai_api.py
@@ -0,0 +1,72 @@
+from invokeai_mcp_server import create_text2img_graph, enqueue_graph, wait_for_completion, get_image_url
+from urllib.parse import urljoin
+
+import asyncio
+
+INVOKEAI_BASE_URL = "http://127.0.0.1:9090"
+
+
+async def generate_image(arguments: dict):
+
+    # Extract parameters
+    prompt = arguments["prompt"]
+    negative_prompt = arguments.get("negative_prompt", "")
+    width = arguments.get("width", 512)
+    height = arguments.get("height", 512)
+    steps = arguments.get("steps", 30)
+    cfg_scale = arguments.get("cfg_scale", 7.5)
+    scheduler = arguments.get("scheduler", "euler")
+    seed = arguments.get("seed")
+    model_key = arguments.get("model_key")
+    lora_key = arguments.get("lora_key")
+    lora_weight = arguments.get("lora_weight", 1.0)
+    vae_key = arguments.get("vae_key")
+
+    #logger.info(f"Generating image with prompt: {prompt[:50]}...")
+
+    # Create graph
+    graph = await create_text2img_graph(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        model_key=model_key,
+        lora_key=lora_key,
+        lora_weight=lora_weight,
+        vae_key=vae_key,
+        width=width,
+        height=height,
+        steps=steps,
+        cfg_scale=cfg_scale,
+        scheduler=scheduler,
+        seed=seed
+    )
+
+    # Enqueue and wait for completion
+    result = await enqueue_graph(graph)
+    batch_id = result["batch"]["batch_id"]
+
+    #logger.info(f"Enqueued batch {batch_id}, waiting for completion...")
+
+    completed = await wait_for_completion(batch_id)
+
+    # Extract image name from result
+    if "result" in completed and "outputs" in completed["result"]:
+        outputs = completed["result"]["outputs"]
+        # Find the image output
+        for node_id, output in outputs.items():
+            if output.get("type") == "image_output":
+                image_name = output["image"]["image_name"]
+                image_url = await get_image_url(image_name)
+
+                text=f"Image generated successfully!\n\nImage Name: {image_name}\nImage URL: {image_url}\n\nYou can view the image at: {urljoin(INVOKEAI_BASE_URL, f'/api/v1/images/i/{image_name}/full')}"
+                print(text)
+
+    # Fallback if we couldn't find image output
+    #text=f"Image generation completed but output format was unexpected. Batch ID: {batch_id}\n\nResult: {json.dumps(completed, indent=2)}"
+    
+async def main():
+    args = {
+        "prompt": "a golden katana with a fancy pommel"
+    }
+    await generate_image(args)
+
+asyncio.run(main())
diff --git a/Assets/_PROJECT/Scenes/DeltaBuilding_base.unity b/Assets/_PROJECT/Scenes/DeltaBuilding_base.unity
index 9357cb38..56a49281 100644
--- a/Assets/_PROJECT/Scenes/DeltaBuilding_base.unity
+++ b/Assets/_PROJECT/Scenes/DeltaBuilding_base.unity
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4b9052863d6b6d99035c9570983fc7dc582ff3573c4b2f3b749239fe3e30ac
-size 63212086
+oid sha256:82fdda2d339b0491cf35eec7b12f32500980662caff77ffda2a62cf34f59c700
+size 63212155
diff --git a/Assets/_PROJECT/Scripts/3DModeGeneration/ModelGenerationPipelineStarter.cs b/Assets/_PROJECT/Scripts/3DModeGeneration/ModelGenerationPipelineStarter.cs
index 9d41e5a1..7349bd5d 100644
--- a/Assets/_PROJECT/Scripts/3DModeGeneration/ModelGenerationPipelineStarter.cs
+++ b/Assets/_PROJECT/Scripts/3DModeGeneration/ModelGenerationPipelineStarter.cs
@@ -11,6 +11,8 @@ public class ModelGenerationPipelineStarter : MonoBehaviour
 
     private MeshRenderer meshRenderer;
 
+    public string inputPrompt;
+
     // Start is called before the first frame update
     void Start()
     {
@@ -48,7 +50,7 @@ public class ModelGenerationPipelineStarter : MonoBehaviour
     {
         return await Task.Run(() =>
         {
-            string inputPrompt = "tasty golden apple, photorealistic, smooth background";
+            
 
             // Path to your virtual environment's python.exe
             string pythonExe = @"D:\users\henrisel\DeltaVR3DModelGeneration\3d-generation-pipeline\.venv\Scripts\python.exe";