refactor: reorganize directory structure and remove hardcoded paths

Move comfyui and vllm out of models/ directory to top level for better
organization. Replace all hardcoded /workspace paths with relative paths
to make the configuration portable across different environments.

Changes:
- Move models/comfyui/ → comfyui/
- Move models/vllm/ → vllm/
- Remove models/ directory (empty)
- Update arty.yml: replace /workspace with environment variables
- Update supervisord.conf: use relative paths from /workspace/ai
- Update all script references to use new paths
- Maintain TQDM_DISABLE=1 to fix BrokenPipeError

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

comfyui/workflows/image-to-video/cogvideox-i2v-production-v1.json

@@ -0,0 +1,201 @@
+{
+  "last_node_id": 10,
+  "last_link_id": 12,
+  "nodes": [
+    {
+      "id": 1,
+      "type": "LoadImage",
+      "pos": [
+        50,
+        100
+      ],
+      "size": [
+        315,
+        314
+      ],
+      "widgets_values": [
+        "input_frame.png",
+        "image"
+      ],
+      "title": "API Input Image",
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      }
+    },
+    {
+      "id": 2,
+      "type": "DiffusersLoader",
+      "pos": [
+        50,
+        500
+      ],
+      "widgets_values": [
+        "diffusion_models/CogVideoX-5b"
+      ],
+      "title": "CogVideoX-5b Loader",
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "DiffusersLoader"
+      },
+      "size": {
+        "0": 350,
+        "1": 100
+      }
+    },
+    {
+      "id": 3,
+      "type": "CLIPTextEncode",
+      "pos": [
+        450,
+        100
+      ],
+      "widgets_values": [
+        "Camera movement description, action, scene details"
+      ],
+      "title": "API Video Prompt",
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "size": {
+        "0": 400,
+        "1": 200
+      }
+    },
+    {
+      "id": 4,
+      "type": "CogVideoXSampler",
+      "pos": [
+        800,
+        100
+      ],
+      "widgets_values": [
+        42,
+        "fixed",
+        50,
+        6.0,
+        49,
+        6
+      ],
+      "title": "CogVideoX Sampler (6s @ 8fps)",
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "CogVideoXSampler"
+      },
+      "size": {
+        "0": 315,
+        "1": 474
+      }
+    },
+    {
+      "id": 5,
+      "type": "VAEDecode",
+      "pos": [
+        1150,
+        100
+      ],
+      "title": "VAE Decode Video",
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      },
+      "size": {
+        "0": 315,
+        "1": 100
+      }
+    },
+    {
+      "id": 6,
+      "type": "VHS_VideoCombine",
+      "pos": [
+        1450,
+        100
+      ],
+      "widgets_values": [
+        8,
+        0,
+        "cogvideox_output",
+        "video/h264-mp4"
+      ],
+      "title": "Combine Video Frames",
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "properties": {
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "size": {
+        "0": 315,
+        "1": 100
+      }
+    }
+  ],
+  "links": [],
+  "extra": {
+    "workflow_info": {
+      "name": "CogVideoX Image-to-Video Production",
+      "version": "1.0.0",
+      "description": "AI-driven image-to-video using CogVideoX-5b. Generate 6-second videos (48 frames @ 8fps) from input images with camera movement and action.",
+      "category": "image-to-video",
+      "tags": [
+        "cogvideox",
+        "i2v",
+        "video-generation",
+        "production"
+      ],
+      "requirements": {
+        "models": [
+          "CogVideoX-5b"
+        ],
+        "custom_nodes": [
+          "ComfyUI-VideoHelperSuite",
+          "ComfyUI-CogVideoXWrapper"
+        ],
+        "vram_min": "20GB"
+      },
+      "parameters": {
+        "input_image": {
+          "node_id": 1,
+          "type": "image",
+          "required": true,
+          "description": "Starting frame for video"
+        },
+        "video_prompt": {
+          "node_id": 3,
+          "type": "string",
+          "required": true,
+          "description": "Describe camera movement and action"
+        },
+        "steps": {
+          "node_id": 4,
+          "type": "integer",
+          "default": 50,
+          "description": "Sampling steps (50 recommended)"
+        },
+        "fps": {
+          "node_id": 6,
+          "type": "integer",
+          "default": 8,
+          "description": "Output framerate"
+        }
+      },
+      "performance": {
+        "avg_generation_time": "120-180 seconds",
+        "vram_usage": "~20-22GB",
+        "output": "6 seconds @ 8fps (48 frames)"
+      }
+    }
+  },
+  "version": 0.4
+}