Wire GPU-aware image gen into setup: auto-install, precision, ComfyUI

Previously display-only: IMG_TIER/IMG_MODELS were detected but never
used. Now they drive actual behavior:

- Both setup scripts call setup-image-models.sh --auto after model
  pulls, installing the right SD/SDXL/Flux model for the detected GPU
- INVOKEAI_PRECISION is now GPU-aware: bfloat16 for Ampere+ (compute
  8.0+), float16 for Pascal+, auto fallback for older cards. Was
  hardcoded to float16.
- local-ai-setup.sh now includes ComfyUI service + Open WebUI
  integration (ENABLE_IMAGE_GENERATION=true, COMFYUI_BASE_URL) — was
  completely missing, only laptop_full_setup.sh had it
- Added ComfyUI port 8188 to UFW firewall rules in local-ai-setup.sh
- Added comfyui-data/comfyui-output directories to mkdir loop
- Updated start.sh and final output to show ComfyUI URL

https://claude.ai/code/session_01PtYTPherSJaxDEVPgF6Nxu

laptop_full_setup.sh

@@ -105,6 +105,19 @@ else
     IMG_DEFAULT=""
 fi
 
+# ── InvokeAI precision (GPU-aware) ───────────────────────────────────────────
+# Ampere+ (compute 8.0+) supports bfloat16 natively for better precision.
+# All modern NVIDIA GPUs support float16. Fall back to auto if unsure.
+GPU_COMPUTE=$(nvidia-smi --query-gpu=compute_cap --format=csv,noheader 2>/dev/null \
+              | head -1 | tr -d '.' || echo "0")
+if   [[ "$GPU_COMPUTE" -ge 80 ]]; then
+    INVOKEAI_PRECISION="bfloat16"   # Ampere+ (RTX 30xx/40xx/50xx, A-series, H100)
+elif [[ "$GPU_COMPUTE" -ge 60 ]]; then
+    INVOKEAI_PRECISION="float16"    # Pascal+ (GTX 10xx, RTX 20xx, Tesla P40/V100)
+else
+    INVOKEAI_PRECISION="auto"       # Let InvokeAI decide
+fi
+
 # ── new vs update ─────────────────────────────────────────────────────────────
 IS_UPDATE=false
 [[ -f "$BASE/docker-compose.yml" ]] && IS_UPDATE=true
@@ -1179,7 +1192,7 @@ IMGENV
     environment:
       - INVOKEAI_HOST=0.0.0.0
       - INVOKEAI_PORT=9090
-      - INVOKEAI_PRECISION=float16
+      - INVOKEAI_PRECISION=$INVOKEAI_PRECISION
     deploy:
       resources:
         reservations:
@@ -1470,6 +1483,21 @@ elif $INSTALL_AI; then
     info "Skipping model pull — run later: bash $BASE/pull-models.sh"
 fi
 
+# ── Install image generation base model (GPU-aware) ──────────────────────────
+if $INSTALL_AI && ($SVC_INVOKEAI || $SVC_COMFYUI) && $PULL_MODELS; then
+    section "Image Generation Models"
+    info "GPU: ${TOTAL_VRAM}GB VRAM → $IMG_TIER"
+    if [[ -n "$IMG_DEFAULT" ]]; then
+        info "Auto-installing recommended model: $IMG_DEFAULT"
+        info "Supported on your GPU: $IMG_MODELS"
+        bash "$SCRIPT_DIR/setup-image-models.sh" --auto
+    else
+        warn "Not enough VRAM for image generation models (need at least 4GB)"
+    fi
+elif $INSTALL_AI && ($SVC_INVOKEAI || $SVC_COMFYUI); then
+    info "Skipping image model install — run later: bash $SCRIPT_DIR/setup-image-models.sh"
+fi
+
 # ── Start ZIM downloads (answer was captured upfront) ────────────────────────
 if $SVC_KIWIX && [[ "$ZIM_CHOICE" != "3" ]]; then
     section "Starting ZIM Downloads"

local-ai-setup.sh

@@ -80,6 +80,17 @@ else
     IMG_DEFAULT=""
 fi
 
+# ── InvokeAI precision (GPU-aware) ───────────────────────────────────────────
+GPU_COMPUTE=$(nvidia-smi --query-gpu=compute_cap --format=csv,noheader 2>/dev/null \
+              | head -1 | tr -d '.' || echo "0")
+if   [[ "$GPU_COMPUTE" -ge 80 ]]; then
+    INVOKEAI_PRECISION="bfloat16"   # Ampere+ (RTX 30xx/40xx/50xx, A-series)
+elif [[ "$GPU_COMPUTE" -ge 60 ]]; then
+    INVOKEAI_PRECISION="float16"    # Pascal+ (GTX 10xx, RTX 20xx, Tesla P40/V100)
+else
+    INVOKEAI_PRECISION="auto"       # Let InvokeAI decide
+fi
+
 section "Local AI Stack — $($IS_UPDATE && echo UPDATE || echo NEW INSTALL)"
 info "Base    : $BASE"
 info "IP      : $LOCAL_IP"
@@ -124,7 +135,7 @@ fi
 
 # ── directories ───────────────────────────────────────────────────────────────
 section "Directories"
-for d in papers repos workspace index invokeai-data invokeai-outputs kiwix gitea portainer-data logs; do
+for d in papers repos workspace index invokeai-data invokeai-outputs comfyui-data comfyui-output kiwix gitea portainer-data logs; do
     mkdir -p "$BASE/$d"
 done
 ok "Ready under $BASE"
@@ -602,6 +613,9 @@ services:
       - WEBUI_AUTH=true
       - ENABLE_RAG_WEB_SEARCH=true
       - RAG_WEB_SEARCH_ENGINE=duckduckgo
+      - ENABLE_IMAGE_GENERATION=true
+      - IMAGE_GENERATION_ENGINE=comfyui
+      - COMFYUI_BASE_URL=http://comfyui:8188
     depends_on:
       ollama: {condition: service_healthy}
 
@@ -726,7 +740,26 @@ services:
     environment:
       - INVOKEAI_HOST=0.0.0.0
       - INVOKEAI_PORT=9090
-      - INVOKEAI_PRECISION=float16
+      - INVOKEAI_PRECISION=$INVOKEAI_PRECISION
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+
+  comfyui:
+    image: ghcr.io/ai-dock/comfyui:latest
+    container_name: comfyui
+    restart: unless-stopped
+    ports: ["0.0.0.0:8188:8188"]
+    volumes:
+      - comfyui-models:/opt/ComfyUI/models
+      - $BASE/comfyui-output:/opt/ComfyUI/output
+      - $BASE/comfyui-data:/opt/ComfyUI/custom_nodes
+    environment:
+      - CLI_ARGS=--listen 0.0.0.0
     deploy:
       resources:
         reservations:
@@ -748,6 +781,7 @@ volumes:
   ollama-models:
   open-webui-data:
   invokeai-models:
+  comfyui-models:
 COMPOSE
 ok "docker-compose.yml"
 
@@ -759,7 +793,7 @@ if command -v ufw &>/dev/null && [[ ! -f "$BASE/.ufw-done" ]] || $FORCE; then
     [[ "$LAN" =~ /[0-9]+$ ]] || LAN="${LAN}/24"
     for pc in "3000:Open WebUI" "11434:Ollama" "8001:RAG" "8002:MCP" \
               "8000:ChromaDB" "8080:Aider" "8181:Kiwix" \
-              "3001:Gitea" "2222:Gitea SSH" "9090:InvokeAI" \
+              "3001:Gitea" "2222:Gitea SSH" "9090:InvokeAI" "8188:ComfyUI" \
               "9000:Portainer" "9443:Portainer S"; do
         sudo ufw allow from "$LAN" to any port "${pc%%:*}" proto tcp comment "${pc##*:}" >/dev/null
     done
@@ -777,7 +811,8 @@ docker compose up -d
 echo ""
 echo "  Open WebUI  →  http://$LOCAL_IP:3000"
 echo "  Aider UI    →  http://$LOCAL_IP:8080  (Claude Code-like editor)"
-echo "  InvokeAI    →  http://$LOCAL_IP:9090"
+echo "  InvokeAI    →  http://$LOCAL_IP:9090  (inpainting, img2img)"
+echo "  ComfyUI     →  http://$LOCAL_IP:8188  (chat-integrated image gen)"
 echo "  Kiwix       →  http://$LOCAL_IP:8181  (run kiwix_download.sh first)"
 echo "  Gitea       →  http://$LOCAL_IP:3001"
 echo "  RAG         →  http://$LOCAL_IP:8001/health"
@@ -900,6 +935,15 @@ if ! $IS_UPDATE && ! $NO_PULL; then
     echo ""
     read -rp "Pull Ollama models now? (~15-30 min) [Y/n]: " DO_PULL
     [[ "${DO_PULL,,}" != "n" ]] && bash "$BASE/pull-models.sh"
+
+    # Install image generation base model (GPU-aware)
+    if [[ -n "$IMG_DEFAULT" ]] && [[ -x "$SCRIPT_DIR/setup-image-models.sh" ]]; then
+        echo ""
+        section "Image Generation Models"
+        info "GPU: ${TOTAL_VRAM}GB VRAM → $IMG_TIER"
+        info "Auto-installing recommended model: $IMG_DEFAULT"
+        bash "$SCRIPT_DIR/setup-image-models.sh" --auto
+    fi
 fi
 
 # =============================================================================
@@ -911,7 +955,8 @@ echo -e "${GREEN}${BOLD}━━━━━━━━━━━━━━━━━━
 echo ""
 echo -e "  ${CYAN}Open WebUI${NC}  →  http://$LOCAL_IP:3000"
 echo -e "  ${CYAN}Aider UI${NC}    →  http://$LOCAL_IP:8080  (browser coding assistant)"
-echo -e "  ${CYAN}InvokeAI${NC}    →  http://$LOCAL_IP:9090"
+echo -e "  ${CYAN}InvokeAI${NC}    →  http://$LOCAL_IP:9090  (inpainting, img2img)"
+echo -e "  ${CYAN}ComfyUI${NC}     →  http://$LOCAL_IP:8188  (chat-integrated image gen)"
 echo -e "  ${CYAN}Kiwix${NC}       →  http://$LOCAL_IP:8181"
 echo -e "  ${CYAN}Gitea${NC}       →  http://$LOCAL_IP:3001"
 echo -e "  ${CYAN}RAG${NC}         →  http://$LOCAL_IP:8001/health"