feat: Add valid ComfyUI SD1.5 workflow to comfy-agent

- Replace placeholder workflow with complete SD1.5 pipeline
- Support dynamic prompt, negative_prompt, steps, seed, width, height
- Nodes: CheckpointLoader -> CLIP -> KSampler -> VAE -> SaveImage

Co-Authored-By: Warp <agent@warp.dev>

services/comfy-agent/app/api.py

@@ -7,12 +7,66 @@ from .worker import enqueue
 router = APIRouter()
 
 def _build_workflow_t2i(req: GenerateImageRequest) -> dict:
-    # MVP: placeholder graph; you will replace with your canonical Comfy workflow JSON.
-    # Keep it deterministic and param-driven.
+    # Basic SD 1.5 workflow
+    # Node structure: CheckpointLoader -> CLIP Encode -> KSampler -> VAE Decode -> SaveImage
     return {
-        "1": {"class_type": "CLIPTextEncode", "inputs": {"text": req.prompt, "clip": ["2", 0]}},
-        "2": {"class_type": "CheckpointLoaderSimple", "inputs": {"ckpt_name": "sdxl.safetensors"}},
-        # TODO: Add complete workflow JSON for text-to-image
+        "3": {
+            "inputs": {
+                "seed": req.seed if req.seed else 42,
+                "steps": req.steps,
+                "cfg": 7.0,
+                "sampler_name": "euler",
+                "scheduler": "normal",
+                "denoise": 1,
+                "model": ["4", 0],
+                "positive": ["6", 0],
+                "negative": ["7", 0],
+                "latent_image": ["5", 0]
+            },
+            "class_type": "KSampler"
+        },
+        "4": {
+            "inputs": {
+                "ckpt_name": "v1-5-pruned-emaonly.safetensors"
+            },
+            "class_type": "CheckpointLoaderSimple"
+        },
+        "5": {
+            "inputs": {
+                "width": req.width,
+                "height": req.height,
+                "batch_size": 1
+            },
+            "class_type": "EmptyLatentImage"
+        },
+        "6": {
+            "inputs": {
+                "text": req.prompt,
+                "clip": ["4", 1]
+            },
+            "class_type": "CLIPTextEncode"
+        },
+        "7": {
+            "inputs": {
+                "text": req.negative_prompt if req.negative_prompt else "text, watermark, blurry",
+                "clip": ["4", 1]
+            },
+            "class_type": "CLIPTextEncode"
+        },
+        "8": {
+            "inputs": {
+                "samples": ["3", 0],
+                "vae": ["4", 2]
+            },
+            "class_type": "VAEDecode"
+        },
+        "9": {
+            "inputs": {
+                "filename_prefix": "comfy-agent",
+                "images": ["8", 0]
+            },
+            "class_type": "SaveImage"
+        }
     }
 
 def _build_workflow_t2v(req: GenerateVideoRequest) -> dict: