diff --git a/README.md b/README.md
index 4bc0ad3..70a30a5 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,8 @@
 # comfyui-workflows
 
-ComfyUI workflow JSON files + model notes
\ No newline at end of file
+ComfyUI workflow JSON files for the nuclide.systems homelab.
+
+- ComfyUI: http://192.168.1.40:18002 (CT 104, LAN only)
+- Current model: v1-5-pruned-emaonly.safetensors (SD 1.5 only)
+
+See ideas/WORKFLOW-IDEAS.md for recommended model additions and planned workflows.
diff --git a/ideas/WORKFLOW-IDEAS.md b/ideas/WORKFLOW-IDEAS.md
new file mode 100644
index 0000000..229a43b
--- /dev/null
+++ b/ideas/WORKFLOW-IDEAS.md
@@ -0,0 +1,35 @@
+# ComfyUI Workflow Ideas
+
+## Models to add
+
+Current: v1-5-pruned-emaonly.safetensors (SD 1.5 baseline quality).
+
+Recommended additions (model path: docker volume comfyui_models):
+- FLUX.1-dev: best photorealism and text rendering
+- SDXL base + refiner: much better composition
+- SDXL Lightning: 4-step fast iteration
+- IP-Adapter: consistent character/face style injection
+- AnimateDiff: animated outputs
+
+## Planned workflows
+
+### Carolina portraits (character consistency)
+Goal: multiple scenes with the same child character
+Approach: IP-Adapter face LoRA + consistent prompt
+Status: blocked on IP-Adapter model
+
+### Children book illustrations (SD 1.5 viable now)
+Style prompt: children book illustration, watercolor painting, soft edges, pastel colors
+Works with current SD 1.5 model
+
+### Food photography (for Meater BBQ results)
+Prompt pattern: [dish], professional food photography, soft studio lighting, 50mm lens, plated
+Needs: SDXL or FLUX.1-dev
+
+### 3D print preview (img2img from slicer screenshot)
+Goal: photorealistic render before printing
+Approach: img2img on slicer preview at denoise 0.5-0.7
+
+### Home scene visualization
+Goal: visualize smart home lighting scenes
+Approach: inpaint room photos with different lighting
diff --git a/workflows/carolina-unicorn-workflow.json b/workflows/carolina-unicorn-workflow.json
new file mode 100644
index 0000000..76efc10
--- /dev/null
+++ b/workflows/carolina-unicorn-workflow.json
@@ -0,0 +1,86 @@
+{
+  "1": {
+    "class_type": "CheckpointLoaderSimple",
+    "inputs": {
+      "ckpt_name": "v1-5-pruned-emaonly.safetensors"
+    }
+  },
+  "2": {
+    "class_type": "CLIPTextEncode",
+    "inputs": {
+      "text": "a young girl with dark hair named Carolina riding a white unicorn, magical forest background, soft watercolor style, childrens book illustration",
+      "clip": [
+        "1",
+        1
+      ]
+    }
+  },
+  "3": {
+    "class_type": "CLIPTextEncode",
+    "inputs": {
+      "text": "ugly, blurry, nsfw, adult, realistic photo",
+      "clip": [
+        "1",
+        1
+      ]
+    }
+  },
+  "4": {
+    "class_type": "EmptyLatentImage",
+    "inputs": {
+      "width": 512,
+      "height": 512,
+      "batch_size": 1
+    }
+  },
+  "5": {
+    "class_type": "KSampler",
+    "inputs": {
+      "model": [
+        "1",
+        0
+      ],
+      "positive": [
+        "2",
+        0
+      ],
+      "negative": [
+        "3",
+        0
+      ],
+      "latent_image": [
+        "4",
+        0
+      ],
+      "seed": 42,
+      "steps": 20,
+      "cfg": 7.0,
+      "sampler_name": "euler",
+      "scheduler": "normal",
+      "denoise": 1.0
+    }
+  },
+  "6": {
+    "class_type": "VAEDecode",
+    "inputs": {
+      "samples": [
+        "5",
+        0
+      ],
+      "vae": [
+        "1",
+        2
+      ]
+    }
+  },
+  "7": {
+    "class_type": "SaveImage",
+    "inputs": {
+      "images": [
+        "6",
+        0
+      ],
+      "filename_prefix": "carolina_unicorn"
+    }
+  }
+}
diff --git a/workflows/carolina-unicorn.md b/workflows/carolina-unicorn.md
new file mode 100644
index 0000000..f21959a
--- /dev/null
+++ b/workflows/carolina-unicorn.md
@@ -0,0 +1,14 @@
+# Carolina on a Unicorn
+
+Generated 2026-05-23. Prompt ID: 4c07a47e-1685-444b-b6f7-a75c818048f0
+
+Prompt: a young girl with dark hair named Carolina riding a white unicorn, magical forest background, soft watercolor style, children book illustration, small portrait format 512x512
+Negative: ugly, blurry, nsfw, adult, realistic photo
+
+Settings:
+- Model: v1-5-pruned-emaonly.safetensors
+- Sampler: euler, 20 steps, cfg=7, seed=42
+- Resolution: 512x512
+- Execution time: ~115 seconds
+
+Quality note: SD 1.5 baseline. Upgrade to SDXL or FLUX.1-dev for significantly better results.