fix prompt

3d-generation-pipeline/.env.example

@@ -0,0 +1,5 @@
+3D_GENERATION_URL=
+MODEL_FOLDER=
+
+CLOUDFLARE_ACCOUNT_ID=
+CLOUDFLARE_API_TOKEN=

3d-generation-pipeline/.gitignore

@@ -0,0 +1,6 @@
+.venv
+.env
+__pycache__
+images/
+models/
+logs/

3d-generation-pipeline/README.md

@@ -0,0 +1,6 @@
+### TODO
+* Artikkel text-to-3d prompt engineeringu kohta: "Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation"
+* TRELLIS: postprocessing_utils: texture baking mode: 'opt' vs 'fast' - hardcoded 'opt', kui võimaldada 'fast' siis tuleb error
+
+### Notes
+* TRELLIS: added functionality to specify texture baking optimisation total steps as an argument (`texture_opt_total_steps`), to replace the hardcoded 2500. But this is not tracked in Git (because modified this https://github.com/IgorAherne/trellis-stable-projectorz/releases/tag/latest)

3d-generation-pipeline/cloudflare_api.py

@@ -0,0 +1,61 @@
+import base64
+import requests
+import os
+
+from dotenv import load_dotenv
+
+load_dotenv()
+ACCOUNT_ID = os.environ["CLOUDFLARE_ACCOUNT_ID"]
+API_TOKEN = os.environ["CLOUDFLARE_API_TOKEN"]
+
+def text_to_image_cloudflare(prompt, output_path):
+    MODEL = "@cf/black-forest-labs/flux-1-schnell"
+    URL = f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/{MODEL}"
+
+    payload = {
+        "prompt": prompt,
+    }
+
+    headers = {
+        "Authorization": f"Bearer {API_TOKEN}",
+        "Content-Type": "application/json",
+    }
+
+    resp = requests.post(URL, json=payload, headers=headers, timeout=60)
+    resp.raise_for_status()
+
+    data = resp.json()
+    b64 = data["result"]["image"]
+    if not b64:
+        raise RuntimeError(f"Unexpected response structure: {data}")
+
+    img_bytes = base64.b64decode(b64)
+
+    with open(output_path, "wb") as f:
+        f.write(img_bytes)
+
+    return True
+
+
+def refine_text_prompt(prompt):
+    MODEL = "@cf/meta/llama-3.2-3b-instruct"
+    URL = f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/{MODEL}"
+
+    instructions = """
+    User is talking about some object. Your task is to generate a short and concise description of it. Use only user's own words, keep it as short as possible.
+    Example:
+    User: 'Umm, okay, I would like a really cool sword, with for example a bright orange crossguard. And also it should be slightly curved.'
+    You: 'a slightly curved sword with bright orange crossguard'
+    """
+
+    response = requests.post(URL,
+    headers={"Authorization": f"Bearer {API_TOKEN}"},
+    json={
+        "messages": [
+        {"role": "system", "content": instructions},
+        {"role": "user", "content": prompt}
+        ]
+    }
+    )
+    data = response.json()
+    return data["result"]["response"]

3d-generation-pipeline/generate_image_local.py

@@ -0,0 +1,86 @@
+import requests
+
+from invokeai_mcp_server import create_text2img_graph, enqueue_graph, wait_for_completion, get_image_url
+from urllib.parse import urljoin
+
+
+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")
+
+    print(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"]
+
+    print(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)
+
+                return urljoin(INVOKEAI_BASE_URL, image_url)
+    
+    raise RuntimeError("Failed to generate image!")
+
+def download_file(url, filepath):
+    response = requests.get(url)
+
+    if response.status_code == 200:
+        with open(filepath, "wb") as file:
+            file.write(response.content)
+    else:
+        raise RuntimeError(f"Failed to download image. Status code: {response.status_code}")
+
+
+async def text_to_image_invoke_ai(prompt, output_path):
+    # see available model keys via GET http://127.0.0.1:9090/api/v2/models/?model_type=main
+    args = {
+        "prompt": prompt,
+        "width": 512,
+        "height": 512,
+        "model_key": "79401292-0a6b-428d-b7d7-f1e86caeba2b" # Juggernaut XL v9
+        #"model_key": "735f6485-6703-498f-929e-07cf0bbbd179" # Dreamshaper 8
+    }
+    image_url = await generate_image(args)
+    print("got image url: ", image_url)
+    download_file(image_url, output_path)

3d-generation-pipeline/generate_model_local.py

@@ -0,0 +1,97 @@
+import subprocess
+import os
+import time
+import requests
+import base64
+
+from dotenv import load_dotenv
+
+load_dotenv()
+MODEL_FOLDER = os.environ["MODEL_FOLDER"]
+API_URL = os.environ["3D_GENERATION_URL"]
+
+
+def image_to_3d_subprocess(image_path, output_path):
+    venv_python = MODEL_FOLDER + r"\.venv\Scripts\python.exe"
+    script_path = MODEL_FOLDER + r"\run.py"
+
+    args = [image_path, "--output-dir", output_path]
+    command = [venv_python, script_path] + args
+
+    try:
+        # Run the subprocess
+        result = subprocess.run(command, capture_output=True, text=True)
+
+        # Print output and errors
+        print("STDOUT:\n", result.stdout)
+        print("STDERR:\n", result.stderr)
+        print("Return Code:", result.returncode)
+
+    except Exception as e:
+        print(f"Error occurred: {e}")
+
+
+
+def generate_no_preview(image_base64: str):
+    """Generate 3D model from a single base64-encoded image without previews.
+    
+    Args:
+        image_base64: Base64 string of the image (without 'data:image/...' prefix)
+    """
+    try:
+        # Set generation parameters
+        params = {
+            'image_base64': image_base64,
+            'seed': 42,
+            'ss_guidance_strength': 7.5,
+            'ss_sampling_steps': 10,
+            'slat_guidance_strength': 7.5,
+            'slat_sampling_steps': 10,
+            'mesh_simplify_ratio': 0.99,
+            'texture_size': 1024,
+            #'texture_baking_mode': 'opt',
+            'texture_opt_total_steps': 1000,
+            'output_format': 'glb'
+        }
+        
+        # Start generation
+        print("Starting generation...")
+        response = requests.post(f"{API_URL}/generate_no_preview", data=params)
+        response.raise_for_status()
+        
+        # Poll status until complete
+        while True:
+            status = requests.get(f"{API_URL}/status").json()
+            print(f"Progress: {status['progress']}%")
+            
+            if status['status'] == 'COMPLETE':
+                break
+            elif status['status'] == 'FAILED':
+                raise Exception(f"Generation failed: {status['message']}")
+            
+            time.sleep(1)
+        
+        # Download the model
+        print("Downloading model...")
+        response = requests.get(f"{API_URL}/download/model")
+        response.raise_for_status()
+        return response.content
+        
+        
+    except Exception as e:
+        print(f"Error: {str(e)}")
+        return None
+    
+def image_to_3d_api(image_path, output_path):
+    with open(image_path, 'rb') as image_file:
+        image_data = image_file.read()
+
+    base64_encoded = base64.b64encode(image_data).decode('utf-8')
+    model_binary = generate_no_preview(base64_encoded)
+
+    output_file = f"{output_path}.glb"
+    with open(output_file, 'wb') as f:
+        f.write(model_binary)
+
+    return output_file
+    

3d-generation-pipeline/notebooks/cloudflare_API_test.ipynb

@@ -0,0 +1,152 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1dc6faae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import base64\n",
+    "import requests\n",
+    "from dotenv import load_dotenv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3107275",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv()\n",
+    "\n",
+    "ACCOUNT_ID = os.environ[\"CLOUDFLARE_ACCOUNT_ID\"]\n",
+    "API_TOKEN = os.environ[\"CLOUDFLARE_API_TOKEN\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "999adf95",
+   "metadata": {},
+   "source": [
+    "## Text to image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "40b35163",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saved: output.jpg  (263282 bytes)\n",
+      "Saved: image9.jpg  (263282 bytes)\n"
+     ]
+    }
+   ],
+   "source": [
+    "MODEL = \"@cf/black-forest-labs/flux-1-schnell\"\n",
+    "URL = f\"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/{MODEL}\"\n",
+    "\n",
+    "payload = {\n",
+    "    \"prompt\": \"a slightly curved broadsword with a fancy golden crossguard\",\n",
+    "}\n",
+    "\n",
+    "headers = {\n",
+    "    \"Authorization\": f\"Bearer {API_TOKEN}\",\n",
+    "    \"Content-Type\": \"application/json\",\n",
+    "}\n",
+    "\n",
+    "resp = requests.post(URL, json=payload, headers=headers, timeout=60)\n",
+    "resp.raise_for_status()\n",
+    "\n",
+    "data = resp.json()\n",
+    "b64 = data[\"result\"][\"image\"]\n",
+    "if not b64:\n",
+    "    raise RuntimeError(f\"Unexpected response structure: {data}\")\n",
+    "\n",
+    "img_bytes = base64.b64decode(b64)\n",
+    "\n",
+    "out_path = \"output.jpg\"\n",
+    "with open(out_path, \"wb\") as f:\n",
+    "    f.write(img_bytes)\n",
+    "\n",
+    "print(f\"Saved: {out_path}  ({len(img_bytes)} bytes)\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "14a874c4",
+   "metadata": {},
+   "source": [
+    "## Text prompt refinement"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "485f6f46",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\"dark wooden battleaxe with bronze blade\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "MODEL = \"@cf/meta/llama-3.2-3b-instruct\"\n",
+    "URL = f\"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/{MODEL}\"\n",
+    "\n",
+    "instructions = \"\"\"\n",
+    "User is talking about some object. Your task is to generate a short and concise description of it. Use only user's own words, keep it as short as possible.\n",
+    "Example:\n",
+    "User: 'Umm, okay, I would like a really cool sword, with for example a bright orange crossguard. And also it should be slightly curved.'\n",
+    "You: 'a slightly curved sword with bright orange crossguard'\n",
+    "\"\"\"\n",
+    "prompt = \"Umm, alright, can you please give me an epic battleaxe? It should have a dark wooden shaft and bronze blade.\"\n",
+    "\n",
+    "response = requests.post(URL,\n",
+    "  headers={\"Authorization\": f\"Bearer {API_TOKEN}\"},\n",
+    "  json={\n",
+    "    \"messages\": [\n",
+    "      {\"role\": \"system\", \"content\": instructions},\n",
+    "      {\"role\": \"user\", \"content\": prompt}\n",
+    "    ]\n",
+    "  }\n",
+    ")\n",
+    "data = response.json()\n",
+    "result_text = data[\"result\"][\"response\"]\n",
+    "print(result_text)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

3d-generation-pipeline/notebooks/local_image_generation.ipynb

@@ -0,0 +1,122 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "50e24baa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from invokeai_mcp_server import create_text2img_graph, enqueue_graph, wait_for_completion, get_image_url\n",
+    "from urllib.parse import urljoin\n",
+    "\n",
+    "import asyncio"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0407cd9a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "INVOKEAI_BASE_URL = \"http://127.0.0.1:9090\"\n",
+    "\n",
+    "\n",
+    "async def generate_image(arguments: dict):\n",
+    "\n",
+    "    # Extract parameters\n",
+    "    prompt = arguments[\"prompt\"]\n",
+    "    negative_prompt = arguments.get(\"negative_prompt\", \"\")\n",
+    "    width = arguments.get(\"width\", 512)\n",
+    "    height = arguments.get(\"height\", 512)\n",
+    "    steps = arguments.get(\"steps\", 30)\n",
+    "    cfg_scale = arguments.get(\"cfg_scale\", 7.5)\n",
+    "    scheduler = arguments.get(\"scheduler\", \"euler\")\n",
+    "    seed = arguments.get(\"seed\")\n",
+    "    model_key = arguments.get(\"model_key\")\n",
+    "    lora_key = arguments.get(\"lora_key\")\n",
+    "    lora_weight = arguments.get(\"lora_weight\", 1.0)\n",
+    "    vae_key = arguments.get(\"vae_key\")\n",
+    "\n",
+    "    #logger.info(f\"Generating image with prompt: {prompt[:50]}...\")\n",
+    "\n",
+    "    # Create graph\n",
+    "    graph = await create_text2img_graph(\n",
+    "        prompt=prompt,\n",
+    "        negative_prompt=negative_prompt,\n",
+    "        model_key=model_key,\n",
+    "        lora_key=lora_key,\n",
+    "        lora_weight=lora_weight,\n",
+    "        vae_key=vae_key,\n",
+    "        width=width,\n",
+    "        height=height,\n",
+    "        steps=steps,\n",
+    "        cfg_scale=cfg_scale,\n",
+    "        scheduler=scheduler,\n",
+    "        seed=seed\n",
+    "    )\n",
+    "\n",
+    "    # Enqueue and wait for completion\n",
+    "    result = await enqueue_graph(graph)\n",
+    "    batch_id = result[\"batch\"][\"batch_id\"]\n",
+    "\n",
+    "    #logger.info(f\"Enqueued batch {batch_id}, waiting for completion...\")\n",
+    "\n",
+    "    completed = await wait_for_completion(batch_id)\n",
+    "\n",
+    "    # Extract image name from result\n",
+    "    if \"result\" in completed and \"outputs\" in completed[\"result\"]:\n",
+    "        outputs = completed[\"result\"][\"outputs\"]\n",
+    "        # Find the image output\n",
+    "        for node_id, output in outputs.items():\n",
+    "            if output.get(\"type\") == \"image_output\":\n",
+    "                image_name = output[\"image\"][\"image_name\"]\n",
+    "                image_url = await get_image_url(image_name)\n",
+    "\n",
+    "                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')}\"\n",
+    "                print(text)\n",
+    "\n",
+    "    # Fallback if we couldn't find image output\n",
+    "    #text=f\"Image generation completed but output format was unexpected. Batch ID: {batch_id}\\n\\nResult: {json.dumps(completed, indent=2)}\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6cf9d879",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def main():\n",
+    "    args = {\n",
+    "        \"prompt\": \"a golden katana with a fancy pommel\"\n",
+    "    }\n",
+    "    await generate_image(args)\n",
+    "\n",
+    "asyncio.run(main())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

3d-generation-pipeline/notebooks/subprocess_test.ipynb

@@ -0,0 +1,165 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4826c91d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2025-10-18-16-35-47'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from datetime import datetime\n",
+    "\n",
+    "datetime.now().strftime(\"%Y-%m-%d-%H-%M-%S\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9419e692",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "STDOUT:\n",
+      " Device used:  cuda\n",
+      "After Remesh 9998 19996\n",
+      "\n",
+      "STDERR:\n",
+      " D:\\users\\henrisel\\stable-fast-3d\\.venv\\lib\\site-packages\\timm\\models\\layers\\__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers\n",
+      "  warnings.warn(f\"Importing from {__name__} is deprecated, please import via timm.layers\", FutureWarning)\n",
+      "\n",
+      "  0%|          | 0/1 [00:00<?, ?it/s]\n",
+      "  0%|          | 0/1 [00:00<?, ?it/s]\n",
+      "Traceback (most recent call last):\n",
+      "  File \"D:\\users\\henrisel\\stable-fast-3d\\run.py\", line 122, in <module>\n",
+      "    mesh, glob_dict = model.run_image(\n",
+      "  File \"D:\\users\\henrisel\\stable-fast-3d\\sf3d\\system.py\", line 286, in run_image\n",
+      "    meshes, global_dict = self.generate_mesh(\n",
+      "  File \"D:\\users\\henrisel\\stable-fast-3d\\sf3d\\system.py\", line 369, in generate_mesh\n",
+      "    rast = self.baker.rasterize(\n",
+      "  File \"D:\\users\\henrisel\\stable-fast-3d\\.venv\\lib\\site-packages\\texture_baker\\baker.py\", line 28, in rasterize\n",
+      "    return torch.ops.texture_baker_cpp.rasterize(\n",
+      "  File \"D:\\users\\henrisel\\stable-fast-3d\\.venv\\lib\\site-packages\\torch\\_ops.py\", line 1243, in __call__\n",
+      "    return self._op(*args, **kwargs)\n",
+      "NotImplementedError: Could not run 'texture_baker_cpp::rasterize' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'texture_baker_cpp::rasterize' is only available for these backends: [CPU, Meta, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy, AutogradMTIA, AutogradMAIA, AutogradMeta, Tracer, AutocastCPU, AutocastMTIA, AutocastMAIA, AutocastXPU, AutocastMPS, AutocastCUDA, FuncTorchBatched, BatchedNestedTensor, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PreDispatch, PythonDispatcher].\n",
+      "\n",
+      "CPU: registered at texture_baker\\csrc\\baker.cpp:543 [kernel]\n",
+      "Meta: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\MetaFallbackKernel.cpp:23 [backend fallback]\n",
+      "BackendSelect: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\BackendSelectFallbackKernel.cpp:3 [backend fallback]\n",
+      "Python: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\PythonFallbackKernel.cpp:194 [backend fallback]\n",
+      "FuncTorchDynamicLayerBackMode: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\functorch\\DynamicLayer.cpp:479 [backend fallback]\n",
+      "Functionalize: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\FunctionalizeFallbackKernel.cpp:375 [backend fallback]\n",
+      "Named: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\NamedRegistrations.cpp:7 [backend fallback]\n",
+      "Conjugate: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\ConjugateFallback.cpp:17 [backend fallback]\n",
+      "Negative: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\native\\NegateFallback.cpp:18 [backend fallback]\n",
+      "ZeroTensor: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\ZeroTensorFallback.cpp:86 [backend fallback]\n",
+      "ADInplaceOrView: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:104 [backend fallback]\n",
+      "AutogradOther: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:63 [backend fallback]\n",
+      "AutogradCPU: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:67 [backend fallback]\n",
+      "AutogradCUDA: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:75 [backend fallback]\n",
+      "AutogradXLA: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:87 [backend fallback]\n",
+      "AutogradMPS: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:95 [backend fallback]\n",
+      "AutogradXPU: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:71 [backend fallback]\n",
+      "AutogradHPU: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:108 [backend fallback]\n",
+      "AutogradLazy: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:91 [backend fallback]\n",
+      "AutogradMTIA: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:79 [backend fallback]\n",
+      "AutogradMAIA: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:83 [backend fallback]\n",
+      "AutogradMeta: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\VariableFallbackKernel.cpp:99 [backend fallback]\n",
+      "Tracer: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\torch\\csrc\\autograd\\TraceTypeManual.cpp:294 [backend fallback]\n",
+      "AutocastCPU: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\autocast_mode.cpp:322 [backend fallback]\n",
+      "AutocastMTIA: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\autocast_mode.cpp:466 [backend fallback]\n",
+      "AutocastMAIA: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\autocast_mode.cpp:504 [backend fallback]\n",
+      "AutocastXPU: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\autocast_mode.cpp:542 [backend fallback]\n",
+      "AutocastMPS: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\autocast_mode.cpp:209 [backend fallback]\n",
+      "AutocastCUDA: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\autocast_mode.cpp:165 [backend fallback]\n",
+      "FuncTorchBatched: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\functorch\\LegacyBatchingRegistrations.cpp:731 [backend fallback]\n",
+      "BatchedNestedTensor: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\functorch\\LegacyBatchingRegistrations.cpp:758 [backend fallback]\n",
+      "FuncTorchVmapMode: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\functorch\\VmapModeRegistrations.cpp:27 [backend fallback]\n",
+      "Batched: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\LegacyBatchingRegistrations.cpp:1075 [backend fallback]\n",
+      "VmapMode: fallthrough registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\VmapModeRegistrations.cpp:33 [backend fallback]\n",
+      "FuncTorchGradWrapper: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\functorch\\TensorWrapper.cpp:210 [backend fallback]\n",
+      "PythonTLSSnapshot: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\PythonFallbackKernel.cpp:202 [backend fallback]\n",
+      "FuncTorchDynamicLayerFrontMode: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\functorch\\DynamicLayer.cpp:475 [backend fallback]\n",
+      "PreDispatch: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\PythonFallbackKernel.cpp:206 [backend fallback]\n",
+      "PythonDispatcher: registered at C:\\actions-runner\\_work\\pytorch\\pytorch\\pytorch\\aten\\src\\ATen\\core\\PythonFallbackKernel.cpp:198 [backend fallback]\n",
+      "\n",
+      "\n",
+      "Return Code: 1\n"
+     ]
+    }
+   ],
+   "source": [
+    "import subprocess\n",
+    "\n",
+    "MODEL_FOLDER = r\"D:\\users\\henrisel\\stable-fast-3d\"\n",
+    "PROJECT_FOLDER = r\"D:\\users\\henrisel\\DeltaVR3DModelGeneration\\3d-generation-pipeline\"\n",
+    "\n",
+    "# Path to the Python interpreter in the other virtual environment\n",
+    "venv_python = MODEL_FOLDER + r\"\\.venv\\Scripts\\python.exe\"\n",
+    "\n",
+    "# Path to the .py file you want to run\n",
+    "script_path = MODEL_FOLDER + r\"\\run.py\"\n",
+    "\n",
+    "# Optional: arguments to pass to the script\n",
+    "args = [MODEL_FOLDER + r\"\\demo_files\\examples\\chair1.png\", \"--output-dir\", PROJECT_FOLDER + r\"\\images\"]\n",
+    "\n",
+    "# Build the command\n",
+    "command = [venv_python, script_path] + args\n",
+    "\n",
+    "try:\n",
+    "    # Run the subprocess\n",
+    "    result = subprocess.run(command, capture_output=True, text=True)\n",
+    "\n",
+    "    # Print output and errors\n",
+    "    print(\"STDOUT:\\n\", result.stdout)\n",
+    "    print(\"STDERR:\\n\", result.stderr)\n",
+    "    print(\"Return Code:\", result.returncode)\n",
+    "\n",
+    "except Exception as e:\n",
+    "    print(f\"Error occurred: {e}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee480ba6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

3d-generation-pipeline/requirements.txt

@@ -0,0 +1,7 @@
+#torch==2.8.0+cu129 https://pytorch.org/get-started/previous-versions/
+transformers==4.57.0
+git+https://github.com/huggingface/diffusers.git
+accelerate==1.10.1
+huggingface_hub[hf_xet]==1.1.10
+sentencepiece==0.2.1
+protobuf==6.32.1

3d-generation-pipeline/start_pipeline.py

@@ -0,0 +1,62 @@
+import argparse
+import asyncio
+import logging
+import time
+
+from pathlib import Path
+from datetime import datetime
+from dotenv import load_dotenv
+
+from generate_image_local import text_to_image_invoke_ai
+from generate_model_local import image_to_3d_api
+
+load_dotenv()
+
+
+def get_timestamp():
+    return datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+
+def setup_logger(base_folder, timestamp):
+    log_dir = base_folder / Path("logs")
+    log_dir.mkdir(parents=True, exist_ok=True)
+    logging.basicConfig(
+        filename=log_dir / f"{timestamp}.log",
+        level=logging.INFO,
+        force=True
+    )
+
+
+async def main():
+    parser = argparse.ArgumentParser(description="Text to 3D model pipeline")
+    parser.add_argument("--prompt", type=str, required=True, help="User text prompt")
+    args = parser.parse_args()
+
+    input_prompt = args.prompt
+    print(f"Input prompt: {input_prompt}")
+    image_generation_prompt = input_prompt + ", single object, fully visible, plain neutral background, high-resolution, sharp details, soft studio lighting, front and side visible, realistic style, true-to-scale"
+    
+    pipeline_folder = Path(__file__).resolve().parent
+    timestamp = get_timestamp()
+    setup_logger(pipeline_folder, timestamp)
+    time_checkpoint = time.time()
+
+    image_path = pipeline_folder / "images" / f"{timestamp}.jpg"
+    # TODO: use Invoke AI or Cloudflare, depending on env var
+    #text_to_image_cloudflare(image_generation_prompt, image_path)
+    await text_to_image_invoke_ai(image_generation_prompt, image_path)
+    
+    image_generation_time = time.time() - time_checkpoint
+    time_checkpoint = time.time()
+    logging.info(f"Image generation time: {round(image_generation_time, 1)} s")
+    print(f"Generated image file: {image_path}")
+
+    model_path = pipeline_folder / "models" / timestamp
+    model_file = image_to_3d_api(image_path, model_path)
+
+    model_generation_time = time.time() - time_checkpoint
+    logging.info(f"Model generation time: {round(model_generation_time, 1)} s")
+    print(f"Generated 3D model file: {model_file}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

Assets/_PROJECT/Components/Bolt/Lexus2016RXTireNormal.png.png.meta

@@ -7,7 +7,7 @@ TextureImporter:
   mipmaps:
     mipMapMode: 0
     enableMipMap: 1
-    sRGBTexture: 1
+    sRGBTexture: 0
     linearTexture: 0
     fadeOut: 0
     borderMipMap: 0
@@ -54,7 +54,7 @@ TextureImporter:
   alphaUsage: 1
   alphaIsTransparency: 0
   spriteTessellationDetail: -1
-  textureType: 0
+  textureType: 1
   textureShape: 1
   singleChannelComponent: 0
   flipbookRows: 1

Assets/_PROJECT/Materials/Green.mat

@@ -0,0 +1,133 @@
+%YAML 1.1
+%TAG !u! tag:unity3d.com,2011:
+--- !u!21 &2100000
+Material:
+  serializedVersion: 8
+  m_ObjectHideFlags: 0
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_Name: Green
+  m_Shader: {fileID: 4800000, guid: 933532a4fcc9baf4fa0491de14d08ed7, type: 3}
+  m_Parent: {fileID: 0}
+  m_ModifiedSerializedProperties: 0
+  m_ValidKeywords: []
+  m_InvalidKeywords: []
+  m_LightmapFlags: 4
+  m_EnableInstancingVariants: 0
+  m_DoubleSidedGI: 0
+  m_CustomRenderQueue: -1
+  stringTagMap:
+    RenderType: Opaque
+  disabledShaderPasses: []
+  m_LockedProperties: 
+  m_SavedProperties:
+    serializedVersion: 3
+    m_TexEnvs:
+    - _BaseMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _BumpMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _DetailAlbedoMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _DetailMask:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _DetailNormalMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _EmissionMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _MainTex:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _MetallicGlossMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _OcclusionMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _ParallaxMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _SpecGlossMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - unity_Lightmaps:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - unity_LightmapsInd:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - unity_ShadowMasks:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    m_Ints: []
+    m_Floats:
+    - _AlphaClip: 0
+    - _AlphaToMask: 0
+    - _Blend: 0
+    - _BlendModePreserveSpecular: 1
+    - _BumpScale: 1
+    - _ClearCoatMask: 0
+    - _ClearCoatSmoothness: 0
+    - _Cull: 2
+    - _Cutoff: 0.5
+    - _DetailAlbedoMapScale: 1
+    - _DetailNormalMapScale: 1
+    - _DstBlend: 0
+    - _DstBlendAlpha: 0
+    - _EnvironmentReflections: 1
+    - _GlossMapScale: 0
+    - _Glossiness: 0
+    - _GlossyReflections: 0
+    - _Metallic: 0
+    - _OcclusionStrength: 1
+    - _Parallax: 0.005
+    - _QueueOffset: 0
+    - _ReceiveShadows: 1
+    - _Smoothness: 0.5
+    - _SmoothnessTextureChannel: 0
+    - _SpecularHighlights: 1
+    - _SrcBlend: 1
+    - _SrcBlendAlpha: 1
+    - _Surface: 0
+    - _WorkflowMode: 1
+    - _ZWrite: 1
+    m_Colors:
+    - _BaseColor: {r: 0, g: 1, b: 0.0381248, a: 1}
+    - _Color: {r: 0, g: 1, b: 0.0381248, a: 1}
+    - _EmissionColor: {r: 0, g: 0, b: 0, a: 1}
+    - _SpecColor: {r: 0.19999996, g: 0.19999996, b: 0.19999996, a: 1}
+  m_BuildTextureStacks: []
+--- !u!114 &6221994712197478572
+MonoBehaviour:
+  m_ObjectHideFlags: 11
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_GameObject: {fileID: 0}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: d0353a89b1f911e48b9e16bdc9f2e058, type: 3}
+  m_Name: 
+  m_EditorClassIdentifier: 
+  version: 7

Assets/_PROJECT/Materials/Green.mat.meta

@@ -0,0 +1,8 @@
+fileFormatVersion: 2
+guid: 937c5f357ed270843bd43d1f7d5d475b
+NativeFormatImporter:
+  externalObjects: {}
+  mainObjectFileID: 2100000
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 

Assets/_PROJECT/Materials/Red.mat

@@ -0,0 +1,133 @@
+%YAML 1.1
+%TAG !u! tag:unity3d.com,2011:
+--- !u!114 &-7093071968994914494
+MonoBehaviour:
+  m_ObjectHideFlags: 11
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_GameObject: {fileID: 0}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: d0353a89b1f911e48b9e16bdc9f2e058, type: 3}
+  m_Name: 
+  m_EditorClassIdentifier: 
+  version: 7
+--- !u!21 &2100000
+Material:
+  serializedVersion: 8
+  m_ObjectHideFlags: 0
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_Name: Red
+  m_Shader: {fileID: 4800000, guid: 933532a4fcc9baf4fa0491de14d08ed7, type: 3}
+  m_Parent: {fileID: 0}
+  m_ModifiedSerializedProperties: 0
+  m_ValidKeywords: []
+  m_InvalidKeywords: []
+  m_LightmapFlags: 4
+  m_EnableInstancingVariants: 0
+  m_DoubleSidedGI: 0
+  m_CustomRenderQueue: -1
+  stringTagMap:
+    RenderType: Opaque
+  disabledShaderPasses: []
+  m_LockedProperties: 
+  m_SavedProperties:
+    serializedVersion: 3
+    m_TexEnvs:
+    - _BaseMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _BumpMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _DetailAlbedoMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _DetailMask:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _DetailNormalMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _EmissionMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _MainTex:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _MetallicGlossMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _OcclusionMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _ParallaxMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - _SpecGlossMap:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - unity_Lightmaps:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - unity_LightmapsInd:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    - unity_ShadowMasks:
+        m_Texture: {fileID: 0}
+        m_Scale: {x: 1, y: 1}
+        m_Offset: {x: 0, y: 0}
+    m_Ints: []
+    m_Floats:
+    - _AlphaClip: 0
+    - _AlphaToMask: 0
+    - _Blend: 0
+    - _BlendModePreserveSpecular: 1
+    - _BumpScale: 1
+    - _ClearCoatMask: 0
+    - _ClearCoatSmoothness: 0
+    - _Cull: 2
+    - _Cutoff: 0.5
+    - _DetailAlbedoMapScale: 1
+    - _DetailNormalMapScale: 1
+    - _DstBlend: 0
+    - _DstBlendAlpha: 0
+    - _EnvironmentReflections: 1
+    - _GlossMapScale: 0
+    - _Glossiness: 0
+    - _GlossyReflections: 0
+    - _Metallic: 0
+    - _OcclusionStrength: 1
+    - _Parallax: 0.005
+    - _QueueOffset: 0
+    - _ReceiveShadows: 1
+    - _Smoothness: 0.5
+    - _SmoothnessTextureChannel: 0
+    - _SpecularHighlights: 1
+    - _SrcBlend: 1
+    - _SrcBlendAlpha: 1
+    - _Surface: 0
+    - _WorkflowMode: 1
+    - _ZWrite: 1
+    m_Colors:
+    - _BaseColor: {r: 1, g: 0, b: 0, a: 1}
+    - _Color: {r: 1, g: 0, b: 0, a: 1}
+    - _EmissionColor: {r: 0, g: 0, b: 0, a: 1}
+    - _SpecColor: {r: 0.19999996, g: 0.19999996, b: 0.19999996, a: 1}
+  m_BuildTextureStacks: []

Assets/_PROJECT/Materials/Red.mat.meta

@@ -0,0 +1,8 @@
+fileFormatVersion: 2
+guid: 707a698b0ec80454a8c68700bca72941
+NativeFormatImporter:
+  externalObjects: {}
+  mainObjectFileID: 2100000
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 

Assets/_PROJECT/Scripts/3DModeGeneration.meta

@@ -0,0 +1,8 @@
+fileFormatVersion: 2
+guid: 0ec3982ba49c4b84ea95332cb090e115
+folderAsset: yes
+DefaultImporter:
+  externalObjects: {}
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 

Assets/_PROJECT/Scripts/3DModeGeneration/ModelGenerationPipelineStarter.cs

@@ -0,0 +1,144 @@
+using UnityEngine;
+using System.Diagnostics;
+using System.Threading.Tasks;
+using GLTFast;
+
+public class ModelGenerationPipelineStarter : MonoBehaviour
+{
+    public Material activeMaterial;
+    public Material inactiveMaterial;
+    public Transform modelSpawnPoint;
+
+    private MeshRenderer meshRenderer;
+
+    public string inputPrompt;
+
+    // Start is called before the first frame update
+    void Start()
+    {
+        meshRenderer = GetComponent<MeshRenderer>();
+    }
+
+    // Update is called once per frame
+    void Update()
+    {
+        
+    }
+
+    void OnTriggerEnter(Collider other)
+    {
+        KbmController controller = other.GetComponent<KbmController>();
+        if (controller != null)
+        {
+            meshRenderer.material = activeMaterial;
+
+            StartModeGenerationPipeline();
+            //LoadModel("D:\\henrisel\\DeltaVR3DModelGeneration\\3d-generation-pipeline\\models\\2025-11-17-16-13-33\\mesh.glb");
+        }
+    }
+
+    private void OnTriggerExit(Collider other)
+    {
+        KbmController controller = other.GetComponent<KbmController>();
+        if (controller != null)
+        {
+            meshRenderer.material = inactiveMaterial;
+        }
+    }
+
+    private async Task<string> GenerateModelAsync()
+    {
+        return await Task.Run(() =>
+        {
+            
+
+            // Path to your virtual environment's python.exe
+            string pythonExe = @"D:\users\henrisel\DeltaVR3DModelGeneration\3d-generation-pipeline\.venv\Scripts\python.exe";
+
+            // Path to your Python script
+            string scriptPath = @"D:\users\henrisel\DeltaVR3DModelGeneration\3d-generation-pipeline\start_pipeline.py";
+
+            // Arguments to pass to the script
+            string arguments = $"{scriptPath} --prompt \"{inputPrompt}\"";
+
+            ProcessStartInfo psi = new ProcessStartInfo
+            {
+                FileName = pythonExe,
+                Arguments = arguments,
+                UseShellExecute = false,
+                RedirectStandardOutput = true,
+                RedirectStandardError = true,
+                CreateNoWindow = true
+            };
+
+            using (Process process = new Process())
+            {
+                process.StartInfo = psi;
+                process.OutputDataReceived += (sender, e) => UnityEngine.Debug.Log(e.Data);
+                process.ErrorDataReceived += (sender, e) => UnityEngine.Debug.LogError(e.Data);
+
+                process.Start();
+
+                string output = process.StandardOutput.ReadToEnd();
+                string error = process.StandardError.ReadToEnd();
+
+                process.WaitForExit();
+
+
+                // Extract model path from output
+                foreach (string line in output.Split('\n'))
+                {
+                    if (line.StartsWith("Generated 3D model file: "))
+                    {
+                        return line.Replace("Generated 3D model file: ", "").Trim();
+                    }
+                }
+
+                return null;
+            }
+        });
+    }
+
+    private async void StartModeGenerationPipeline()
+    {
+        string modelPath = await GenerateModelAsync();
+
+        if (!string.IsNullOrEmpty(modelPath))
+        {
+            UnityEngine.Debug.Log("Got generated model path: " + modelPath);
+            await LoadModel(modelPath);
+        }
+        else
+        {
+            UnityEngine.Debug.LogError("Model path not found in Python output.");
+        }
+
+    }
+
+    private async Task LoadModel(string modelPath)
+    {
+        var gltf = new GltfImport();
+        bool loadSuccess = await gltf.Load(modelPath);
+        UnityEngine.Debug.Log("Load model success: " + loadSuccess);
+        if (loadSuccess)
+        {
+            GameObject spawnedObject = new GameObject("spawned model");
+            spawnedObject.transform.parent = modelSpawnPoint;
+            spawnedObject.transform.position = modelSpawnPoint.position;
+
+            bool spawnSuccess = await gltf.InstantiateMainSceneAsync(spawnedObject.transform);
+            UnityEngine.Debug.Log("Spawn model success: " + spawnSuccess);
+
+
+            Transform spawnedObjectMainTransform = spawnedObject.transform.GetChild(0).transform;
+            GameObject spawnedObjectBody = spawnedObjectMainTransform.GetChild(0).transform.gameObject;
+            MeshCollider collider = spawnedObjectBody.AddComponent<MeshCollider>();
+            collider.convex = true;
+            MeshRenderer renderer = spawnedObjectBody.GetComponent<MeshRenderer>();
+            renderer.material.SetFloat("metallicFactor", 0);
+
+            spawnedObjectMainTransform.gameObject.AddComponent<Rigidbody>();
+        }
+
+    }
+}

Assets/_PROJECT/Scripts/3DModeGeneration/ModelGenerationPipelineStarter.cs.meta

@@ -0,0 +1,11 @@
+fileFormatVersion: 2
+guid: 46e67223dce9b7a4783ed36b8ed65f19
+MonoImporter:
+  externalObjects: {}
+  serializedVersion: 2
+  defaultReferences: []
+  executionOrder: 0
+  icon: {instanceID: 0}
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 

Packages/manifest.json

@@ -4,6 +4,7 @@
     "com.unity.2d.tilemap": "1.0.0",
     "com.unity.ai.navigation": "1.1.1",
     "com.unity.cinemachine": "2.9.5",
+    "com.unity.cloud.gltfast": "6.14.1",
     "com.unity.collab-proxy": "2.0.1",
     "com.unity.ext.nunit": "1.0.6",
     "com.unity.feature.vr": "1.0.0",

Packages/packages-lock.json

@@ -31,11 +31,12 @@
       "url": "https://packages.unity.com"
     },
     "com.unity.burst": {
-      "version": "1.8.3",
+      "version": "1.8.24",
       "depth": 1,
       "source": "registry",
       "dependencies": {
-        "com.unity.mathematics": "1.2.1"
+        "com.unity.mathematics": "1.2.1",
+        "com.unity.modules.jsonserialize": "1.0.0"
       },
       "url": "https://packages.unity.com"
     },
@@ -48,6 +49,19 @@
       },
       "url": "https://packages.unity.com"
     },
+    "com.unity.cloud.gltfast": {
+      "version": "6.14.1",
+      "depth": 0,
+      "source": "registry",
+      "dependencies": {
+        "com.unity.burst": "1.8.24",
+        "com.unity.collections": "1.2.4",
+        "com.unity.mathematics": "1.2.6",
+        "com.unity.modules.jsonserialize": "1.0.0",
+        "com.unity.modules.unitywebrequest": "1.0.0"
+      },
+      "url": "https://packages.unity.com"
+    },
     "com.unity.collab-proxy": {
       "version": "2.0.1",
       "depth": 0,
@@ -55,6 +69,16 @@
       "dependencies": {},
       "url": "https://packages.unity.com"
     },
+    "com.unity.collections": {
+      "version": "1.2.4",
+      "depth": 1,
+      "source": "registry",
+      "dependencies": {
+        "com.unity.burst": "1.6.6",
+        "com.unity.test-framework": "1.1.31"
+      },
+      "url": "https://packages.unity.com"
+    },
     "com.unity.editorcoroutines": {
       "version": "1.0.0",
       "depth": 1,

README.md

@@ -66,17 +66,23 @@ Multiplayer and cross-play functionality. [Bachelor's Thesis](https://comserv.cs
 **Raimond Tunnel**<br/>
 Project management, visual design.
 
-**Timur Nizamov**<br/>
-Technical sound design.
-
 Developed in the [Computer Graphcis and Virtual Reality Study Lab](https://cgvr.cs.ut.ee/) of the [Institute of Computer Science, University of Tartu](https://cs.ut.ee).
 
 ### Used Attributions
 
 | Description                                         | License                                      | Source                                                                                      | Author           |
 |-----------------------------------------------------|----------------------------------------------|---------------------------------------------------------------------------------------------|------------------|
+| Bold's car driving sound                            | Attribution NonCommercial 3.0                | [Link](https://freesound.org/people/Pfujimoto/sounds/14371/)                               | Pfujimoto        |
+| Bold's car braking sound                            | Attribution 3.0                              | [Link](https://freesound.org/people/200154michaela/sounds/542448/)                         | 200154michaela   |
+| Bold's car horn sound                               | Attribution 4.0                              | [Link](https://freesound.org/people/ceberation/sounds/235506/)                             | ceberation       |
 | Server rack model                                   | Royalty Free, No AI License                  | [Link](https://www.cgtrader.com/free-3d-models/electronics/computer/simple-server-model)   | anymelok         |
+| Server rack humming sound                           | Attribution 4.0                              | [Link](https://freesound.org/people/jameswrowles/sounds/248217/)                           | jameswrowles     |
+| Fire suppression button press sound                 | Creative Commons 0                           | [Link](https://freesound.org/people/LamaMakesMusic/sounds/403556/)                         | LamaMakesMusic   |
+| Fire suppression alarm sound                        | Attribution 3.0                              | [Link](https://freesound.org/people/jobro/sounds/33737/)                                   | jobro            |
+| Fire-suppressing gas release sound                  | Creative Commons 0                           | [Link](https://freesound.org/people/mrmccormack/sounds/182359/)                            | mrmccormack      |
+| Coughing sound in response to fire-suppressing gas  | Attribution 4.0                              | [Link](https://freesound.org/people/qubodup/sounds/739416/)                                | qubodup          |
 | Robot movement sound                                | Creative Commons 0                           | [Link](https://freesound.org/people/Brazilio123/sounds/661435/)                            | Brazilio123      |
+| Portal humming sound                                | Attribution 4.0                              | [Link](https://freesound.org/people/zimbot/sounds/122972/)                                 | zimbot           |
 | Spacewalk UFO sound                                 | Attribution NonCommercial 4.0                           | [Link](https://freesound.org/people/Speedenza/sounds/209366/)                           | Speedenza     |
 | Keyboard icons                                      | Creative Commons Attribution-NoDerivs 3.0    | [Link](https://icons8.com/)                                                                 | icons8           |