root/ubuntu-post-install
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #77 from outis1one/claude/exciting-allen-uea3dx

Browse Source 
Claude/exciting allen uea3dx
This commit is contained in:
Outis
2026-06-09 13:37:42 -04:00
committed by GitHub
parent b6f499295f f9013287d9
commit 1664001a9e
3 changed files with 1049 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -67,7 +67,7 @@ Update them any time with `sudo ./setup.sh configure`.
|-------|---------| |-------|---------|
| `base` | `net-tools`, `ncdu`, `git`, `curl`, `wget`, `htop`, `tree`, `zip`/`unzip`, `ca-certificates`, `gnupg`, `jq`, `rsync`; `glow` (terminal markdown reader, Charm apt repo) | | `base` | `net-tools`, `ncdu`, `git`, `curl`, `wget`, `htop`, `tree`, `zip`/`unzip`, `ca-certificates`, `gnupg`, `jq`, `rsync`; `glow` (terminal markdown reader, Charm apt repo) |
| `homelab` | `caddy`, `crowdsec`, `authelia`, `homeassistant`, `asterisk` | | `homelab` | `caddy`, `crowdsec`, `authelia`, `homeassistant`, `asterisk` |
| `utilities` | `actualbudget`, `archivebox`, `changedetection`, `ddclient`, `filebrowser`, `fmd`, `gatus`, `homebox`, `joplin`, `koha`, `magicmirror`, `mail-archiver`, `mattermost`, `mealie`, `meshcentral`, `n8n`, `nextcloud`, `ntfy`, `onlyoffice`, `portainer`, `rustdesk`, `stirling-pdf`, `syncthing`, `traccar`, `unifi`, `uptimekuma`, `vaultwarden`, `watchyourlan`, `watchtower`, `wg-easy` | | `utilities` | `actualbudget`, `ai-gpu`, `archivebox`, `changedetection`, `ddclient`, `filebrowser`, `fmd`, `gatus`, `homebox`, `iopaint`, `joplin`, `koha`, `magicmirror`, `mail-archiver`, `mattermost`, `mealie`, `meshcentral`, `n8n`, `nextcloud`, `ntfy`, `onlyoffice`, `portainer`, `rustdesk`, `stirling-pdf`, `syncthing`, `traccar`, `unifi`, `uptimekuma`, `vaultwarden`, `watchyourlan`, `watchtower`, `wg-easy` |
| `media` | `arm`, `audiobookshelf`, `calibre-web`, `emby`, `immich`, `jellyfin`, `lyrion` | | `media` | `arm`, `audiobookshelf`, `calibre-web`, `emby`, `immich`, `jellyfin`, `lyrion` |
| `cameras` | `frigate`, `frigate-audio`, `frigate-notify`, `sky-cam` | | `cameras` | `frigate`, `frigate-audio`, `frigate-notify`, `sky-cam` |
| `gaming` | `drum-rhythm-game`, `js99er`, `minecraft`, `wolf`, `wolf-pair` | | `gaming` | `drum-rhythm-game`, `js99er`, `minecraft`, `wolf`, `wolf-pair` |
services/ai-gpu.sh
+573
View File
@@ -0,0 +1,573 @@
#!/bin/bash
# services/ai-gpu.sh — GPU AI stack: InvokeAI image gen + Ollama/OpenWebUI LLM + swap portal.
# Part of the modular post-install system (sourced by setup.sh).
#
# Can also be run standalone on any machine:
# sudo bash ai-gpu.sh
# (Docker + nvidia-container-toolkit must already be installed)
#
# Clones https://github.com/outis1one/ai-6gb-gpu and installs three stacks:
# image-gen/ — InvokeAI (port 9090), nvidia GPU, optimised for 6 GB VRAM
# llm/ — Ollama (11434) + Open WebUI (3000) + SearXNG (internal)
# portal/ — Flask app (port 8080), mounts Docker socket, hot-swaps GPU between stacks
#
# Because a 6 GB GPU can only run ONE stack at a time, the portal handles the swap:
# stop the active stack, start the requested one. Stop image-gen before starting llm, and vice versa.
# ── Standalone bootstrap ──────────────────────────────────────────────────────
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
[[ "$(id -u)" == "0" ]] || { echo "Run with sudo: sudo bash $0"; exit 1; }
_SELF_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
_COMMON="$_SELF_DIR/../lib/common.sh"
if [[ -f "$_COMMON" ]]; then
source "$_COMMON"
else
log_info() { echo -e "\033[0;34m[INFO]\033[0m $*"; }
log_success() { echo -e "\033[0;32m[OK]\033[0m $*"; }
log_warning() { echo -e "\033[1;33m[WARN]\033[0m $*"; }
log_error() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; }
require_docker() {
command -v docker &>/dev/null || {
log_error "Docker not found. Install it first:"
log_error " curl -fsSL https://get.docker.com | sudo sh"
return 1
}
docker compose version &>/dev/null || {
log_error "Docker Compose plugin missing:"
log_error " sudo apt-get install -y docker-compose-plugin"
return 1
}
}
ensure_docker_dir_ownership() {
chown -R "$ACTUAL_USER:$ACTUAL_USER" "$@" 2>/dev/null || true
}
prompt_text() {
local _q="$1" _def="$2" _var="$3" _r
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
read -r -p " $_q " _r
eval "$_var='${_r:-$_def}'"
}
prompt_yn() {
local _q="$1" _def="$2" _var="$3" _r
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
read -r -p " $_q " _r
eval "$_var='${_r:-$_def}'"
}
configure_caddy_for_service() {
local _name="$1" _upstream="$2" _subdomain="$3" _extra="${4:-}"
local _caddy_dir="$DOCKER_DIR/caddy"
local _caddyfile="$_caddy_dir/Caddyfile"
local _display_port="${_upstream##*:}"
local _mode="none"
[[ -d "$_caddy_dir" ]] && _mode="local"
[[ -n "${CADDY_REMOTE_HOST:-}" ]] && [[ "$_mode" != "local" ]] && _mode="remote"
[[ "$_mode" == "none" ]] && {
log_info "Access $_name directly on port $_display_port."
return 0
}
echo ""
local _do_caddy=""
if [[ "$_mode" == "remote" ]]; then
log_info "Remote Caddy configured (${CADDY_REMOTE_HOST})."
log_info "A snippet file will be saved to ~/docker/caddy-snippets/."
fi
read -r -p " Configure Caddy reverse proxy for $_name? [y/N]: " _do_caddy
[[ "${_do_caddy,,}" == "y" ]] || {
log_info "Skipping — access at: http://localhost:$_display_port"
return 0
}
local _default_domain=""
if [[ -n "${SITE_DOMAIN:-}" ]] && [[ "$SITE_DOMAIN" != "example.com" ]]; then
_default_domain="${_subdomain}.${SITE_DOMAIN}"
log_info "Default: $_default_domain"
fi
local _domain=""
read -r -p " Domain [${_default_domain:-required}]: " _domain
_domain="${_domain:-$_default_domain}"
[[ -n "$_domain" ]] || { log_warning "No domain entered — skipping Caddy."; return 0; }
local _block_upstream="$_upstream"
if [[ "$_mode" == "remote" ]]; then
_block_upstream="${CADDY_REMOTE_HOST}:${_display_port}"
fi
local _site_block
_site_block="$(cat << CBLOCK
# $_name
${_domain} {
reverse_proxy ${_block_upstream}
header {
Strict-Transport-Security "max-age=31536000; includeSubDomains; preload"
X-Content-Type-Options "nosniff"
X-Frame-Options "SAMEORIGIN"
Referrer-Policy "strict-origin-when-cross-origin"
}
log {
output file /var/log/caddy/${_domain}.log
format json
}
${_extra}
}
CBLOCK
)"
if [[ "$_mode" == "local" ]]; then
if [[ -f "$_caddyfile" ]]; then
local _bk="$_caddy_dir/Caddyfile.backup.$(date +%Y%m%d-%H%M%S)"
cp "$_caddyfile" "$_bk"
log_info "Backed up Caddyfile to $(basename "$_bk")"
else
touch "$_caddyfile"
fi
if grep -q "^${_domain}" "$_caddyfile" 2>/dev/null; then
log_warning "$_domain already in Caddyfile"
local _ow=""
read -r -p " Overwrite? [y/N]: " _ow
[[ "${_ow,,}" == "y" ]] || { log_info "Keeping existing entry."; return 0; }
sed -i "/^${_domain}/,/^}/d" "$_caddyfile"
fi
printf '%s\n' "$_site_block" >> "$_caddyfile"
log_success "Added $_domain to Caddyfile"
docker exec caddy caddy fmt --overwrite /etc/caddy/Caddyfile 2>/dev/null || true
if docker exec caddy caddy reload --config /etc/caddy/Caddyfile 2>/dev/null; then
log_success "$_name accessible at: https://$_domain"
else
log_warning "Reload failed — check: docker logs caddy"
log_info "Manual reload: docker exec caddy caddy reload --config /etc/caddy/Caddyfile"
fi
else
local _snippet_dir="$DOCKER_DIR/caddy-snippets"
local _snippet_file="$_snippet_dir/${_subdomain}.caddy"
mkdir -p "$_snippet_dir"
printf '%s\n' "$_site_block" > "$_snippet_file"
chown "$ACTUAL_USER:$ACTUAL_USER" "$_snippet_file" 2>/dev/null || true
log_success "Snippet saved: $_snippet_file"
log_info "Copy to Caddy machine:"
log_info " scp $_snippet_file caddy-host:~/caddy-snippets/"
log_info " rsync -av $_snippet_dir/ caddy-host:~/caddy-snippets/ (all at once)"
fi
}
write_readme() {
local _dir="$1"
mkdir -p "$_dir"
[[ "${DRY_RUN:-false}" == "true" ]] && return 0
cat > "$_dir/README.md"
}
generate_password() {
local _len="${1:-32}"
tr -dc 'A-Za-z0-9' < /dev/urandom | head -c "$_len"
echo
}
fi
ACTUAL_USER="${ACTUAL_USER:-${SUDO_USER:-$USER}}"
ACTUAL_HOME="$(getent passwd "$ACTUAL_USER" 2>/dev/null | cut -d: -f6 || echo "${HOME:-/root}")"
DOCKER_DIR="${DOCKER_DIR:-$ACTUAL_HOME/docker}"
DRY_RUN="${DRY_RUN:-false}"
UNATTENDED="${UNATTENDED:-false}"
SITE_TZ="${SITE_TZ:-$(cat /etc/timezone 2>/dev/null || echo UTC)}"
SITE_DOMAIN="${SITE_DOMAIN:-example.com}"
SITE_CADDY_NET="${SITE_CADDY_NET:-caddy_net}"
CADDY_REMOTE_HOST="${CADDY_REMOTE_HOST:-}"
register_service() { :; }
_RUN_STANDALONE=1
fi
# ─────────────────────────────────────────────────────────────────────────────
register_service ai-gpu utilities "GPU AI stack — InvokeAI image gen + Ollama/OpenWebUI LLM (6 GB VRAM)" 9090
install_ai_gpu() {
require_docker || return 1
log_info "Installing AI GPU stack (InvokeAI + Ollama/OpenWebUI + portal)..."
log_info "Requires: nvidia GPU with 6 GB+ VRAM, nvidia-container-toolkit installed."
local AI_DIR="$DOCKER_DIR/ai-gpu"
local REPO_URL="https://github.com/outis1one/ai-6gb-gpu.git"
local REPO_DIR="$AI_DIR/src"
if [ "$DRY_RUN" = true ]; then
echo "[DRY-RUN] Would clone $REPO_URL to $REPO_DIR"
echo "[DRY-RUN] Would create stacks: image-gen (InvokeAI:9090), llm (Ollama:11434 + OpenWebUI:3000), portal (8080)"
echo "[DRY-RUN] Would prompt for Ollama and InvokeAI model selection"
echo "[DRY-RUN] Would auto-pull selected Ollama models after LLM stack starts"
echo "[DRY-RUN] Would queue InvokeAI starter model via REST API"
return 0
fi
# ── Timezone ──────────────────────────────────────────────────────────────
local TZ_VAL="${SITE_TZ:-UTC}"
prompt_text "Timezone (e.g. America/New_York) [$TZ_VAL]:" "$TZ_VAL" TZ_VAL
TZ_VAL="${TZ_VAL:-UTC}"
# ── Ollama model selection ────────────────────────────────────────────────
echo ""
log_info "Ollama LLM models — select which to download (enter numbers separated by spaces):"
log_info "All models are quantized (Q4_K_M) and run comfortably on 6 GB VRAM."
echo ""
log_info " 1) llama3.2:3b ~2.0 GB Fast general chat. Great all-rounder. ← Recommended"
log_info " 2) llama3.2:1b ~1.3 GB Ultra-fast. Light tasks, low latency."
log_info " 3) qwen2.5:7b ~4.7 GB Top code + math model. Strong reasoning."
log_info " 4) mistral:7b ~4.1 GB Solid all-rounder. Good at instruction follow."
log_info " 5) phi4-mini ~2.5 GB Microsoft Phi-4 mini. Excellent for coding."
log_info " 6) gemma3:4b ~2.5 GB Google Gemma 3. Well-rounded, multilingual."
log_info " 7) deepseek-r1:7b ~4.7 GB Strong reasoning and math. Think-step model."
log_info " 8) nomic-embed-text ~274 MB Embedding model — enables RAG/doc search."
log_info " Recommended to add alongside a chat model."
echo ""
log_info " Example: '1 8' pulls llama3.2:3b + nomic-embed-text"
log_info " Enter '0' or leave blank to skip and pull models manually later."
echo ""
local OLLAMA_CHOICES=""
prompt_text "Models to download [1 8]:" "1 8" OLLAMA_CHOICES
declare -a OLLAMA_MODELS=()
for _n in $OLLAMA_CHOICES; do
case "$_n" in
1) OLLAMA_MODELS+=("llama3.2:3b") ;;
2) OLLAMA_MODELS+=("llama3.2:1b") ;;
3) OLLAMA_MODELS+=("qwen2.5:7b") ;;
4) OLLAMA_MODELS+=("mistral:7b") ;;
5) OLLAMA_MODELS+=("phi4-mini") ;;
6) OLLAMA_MODELS+=("gemma3:4b") ;;
7) OLLAMA_MODELS+=("deepseek-r1:7b") ;;
8) OLLAMA_MODELS+=("nomic-embed-text") ;;
esac
done
# ── InvokeAI model selection ──────────────────────────────────────────────
echo ""
log_info "InvokeAI image generation models (for 6 GB VRAM with partial GPU offload):"
log_info "InvokeAI uses VRAM=3 GB + 8 GB RAM cache, so all models below work on 6 GB."
echo ""
log_info " 1) stabilityai/stable-diffusion-v1-5 ~4 GB SD 1.5 — fast, huge style/LoRA library."
log_info " Best starting model for most uses."
log_info " 2) stabilityai/sdxl-turbo ~7 GB SDXL Turbo — 4-step generation."
log_info " Fast, high quality, slightly slower on 6 GB."
log_info " 3) stabilityai/stable-diffusion-xl-base-1.0"
log_info " ~7 GB SDXL base — best quality at 1024px."
log_info " Slowest due to RAM offload on 6 GB."
log_info " 4) Skip — install models via the Model Manager at http://localhost:9090"
echo ""
log_info " Tip: SD 1.5 (choice 1) is fastest and most compatible. Start here."
log_info " HuggingFace token: required for some gated models (free at huggingface.co/settings/tokens)"
echo ""
local INVOKE_CHOICE=""
prompt_text "InvokeAI starter model [1]:" "1" INVOKE_CHOICE
local INVOKE_MODEL_SOURCE=""
local INVOKE_MODEL_NAME=""
case "$INVOKE_CHOICE" in
2) INVOKE_MODEL_SOURCE="stabilityai/sdxl-turbo"
INVOKE_MODEL_NAME="SDXL Turbo" ;;
3) INVOKE_MODEL_SOURCE="stabilityai/stable-diffusion-xl-base-1.0"
INVOKE_MODEL_NAME="SDXL Base" ;;
4) INVOKE_MODEL_SOURCE=""
INVOKE_MODEL_NAME="" ;;
*) INVOKE_MODEL_SOURCE="stabilityai/stable-diffusion-v1-5"
INVOKE_MODEL_NAME="SD 1.5" ;;
esac
local HF_TOKEN=""
if [ -n "$INVOKE_MODEL_SOURCE" ]; then
prompt_text "HuggingFace token (optional — needed for gated models, enter to skip):" "" HF_TOKEN
fi
# ── Clone / update repo ───────────────────────────────────────────────────
mkdir -p "$AI_DIR"
if [ -d "$REPO_DIR/.git" ]; then
log_info "Updating ai-6gb-gpu repo..."
git -C "$REPO_DIR" pull --ff-only 2>/dev/null \
&& log_success "Repo updated" \
|| log_warning "Could not pull latest — using existing version"
else
log_info "Cloning ai-6gb-gpu repo..."
git clone --depth 1 "$REPO_URL" "$REPO_DIR" \
|| { log_error "Clone failed — check network and git access"; return 1; }
fi
# ── Image-gen stack (InvokeAI) ────────────────────────────────────────────
local IMAGE_GEN_DIR="$AI_DIR/image-gen"
mkdir -p "$IMAGE_GEN_DIR"
if [ -d "$REPO_DIR/ai-image-gen" ]; then
cp -rn "$REPO_DIR/ai-image-gen/." "$IMAGE_GEN_DIR/" 2>/dev/null || true
find "$IMAGE_GEN_DIR" -name "docker-compose.yml" -exec \
sed -i "s|America/New_York|$TZ_VAL|g" {} \;
fi
cat > "$IMAGE_GEN_DIR/.env" << IMGENV
# InvokeAI — image generation
TZ=${TZ_VAL}
# VRAM cap: 3 GB leaves headroom on a 6 GB card; remaining model layers go to RAM
INVOKEAI_vram=3
# RAM cache size for model layer offload
INVOKEAI_ram=8
${HF_TOKEN:+HUGGING_FACE_HUB_TOKEN=${HF_TOKEN}}
CADDY_NET=${SITE_CADDY_NET}
IMGENV
chmod 600 "$IMAGE_GEN_DIR/.env"
# ── LLM stack (Ollama + Open WebUI + SearXNG) ─────────────────────────────
local LLM_DIR="$AI_DIR/llm"
mkdir -p "$LLM_DIR"
if [ -d "$REPO_DIR/ai-llm" ]; then
cp -rn "$REPO_DIR/ai-llm/." "$LLM_DIR/" 2>/dev/null || true
find "$LLM_DIR" -name "docker-compose.yml" -exec \
sed -i "s|America/New_York|$TZ_VAL|g" {} \;
fi
local WEBUI_SECRET
WEBUI_SECRET="$(generate_password 32)"
cat > "$LLM_DIR/.env" << LLMENV
# Ollama + Open WebUI + SearXNG
TZ=${TZ_VAL}
WEBUI_SECRET_KEY=${WEBUI_SECRET}
# Open WebUI: enable SearXNG for web search in chats
ENABLE_RAG_WEB_SEARCH=true
RAG_WEB_SEARCH_ENGINE=searxng
SEARXNG_QUERY_URL=http://searxng:8080/search?q=<query>&format=json
CADDY_NET=${SITE_CADDY_NET}
LLMENV
chmod 600 "$LLM_DIR/.env"
# ── Portal stack (Flask GPU swap controller) ──────────────────────────────
local PORTAL_DIR="$AI_DIR/portal"
mkdir -p "$PORTAL_DIR"
if [ -d "$REPO_DIR/ai-portal" ]; then
cp -rn "$REPO_DIR/ai-portal/." "$PORTAL_DIR/" 2>/dev/null || true
if [ -f "$PORTAL_DIR/docker-compose.yml" ]; then
sed -i \
"s|/home/[^/]*/docker:|${ACTUAL_HOME}/docker:|g" \
"$PORTAL_DIR/docker-compose.yml"
sed -i "s|America/New_York|$TZ_VAL|g" "$PORTAL_DIR/docker-compose.yml"
fi
fi
cat > "$PORTAL_DIR/.env" << PORTALENV
# AI Portal — GPU stack swap controller
TZ=${TZ_VAL}
# Paths inside the container (/docker maps to ${ACTUAL_HOME}/docker via volume mount)
IMAGE_STACK=/docker/ai-gpu/image-gen
LLM_STACK=/docker/ai-gpu/llm
CADDY_NET=${SITE_CADDY_NET}
PORTALENV
chmod 600 "$PORTAL_DIR/.env"
ensure_docker_dir_ownership "$AI_DIR"
echo ""
log_success "AI GPU stacks configured under $AI_DIR"
log_warning "Only ONE GPU stack can run at a time on a 6 GB card."
log_info "Use the portal (port 8080) to hot-swap between image-gen and llm."
echo ""
# ── Caddy ─────────────────────────────────────────────────────────────────
configure_caddy_for_service "AI Portal" "ai-portal:8080" "localai"
configure_caddy_for_service "InvokeAI" "invokeai:9090" "images"
# ── README ────────────────────────────────────────────────────────────────
write_readme "$AI_DIR" << MD
# AI GPU Stack
Three Docker stacks optimised for a 6 GB VRAM nvidia GPU.
Source: https://github.com/outis1one/ai-6gb-gpu
## Stacks
| Stack | Service | Port | Notes |
|-------|---------|------|-------|
| \`image-gen/\` | InvokeAI | 9090 | Image generation (SD 1.5, SDXL, Flux…) |
| \`llm/\` | Ollama | 11434 | LLM inference engine |
| \`llm/\` | Open WebUI | 3000 | Chat UI — models, RAG, web search |
| \`llm/\` | SearXNG | internal | Web search backend for RAG in OpenWebUI |
| \`portal/\` | AI Portal | 8080 | GPU swap controller — start/stop stacks |
## GPU time-sharing (important)
A 6 GB GPU can only run one AI stack at a time.
Use the portal at http://localhost:8080 to swap.
Manual swap:
\`\`\`bash
docker compose -f $AI_DIR/llm/docker-compose.yml down
docker compose -f $AI_DIR/image-gen/docker-compose.yml up -d
\`\`\`
## InvokeAI — add more models
Models installed at setup are in the Model Manager. To add more:
1. Open http://localhost:9090 → Model Manager → Add Model
2. Paste a HuggingFace repo ID (e.g. \`stabilityai/stable-diffusion-2-1\`)
3. Or import a local .safetensors file
For gated models, add \`HUGGING_FACE_HUB_TOKEN=xxx\` to \`image-gen/.env\`.
Recommended models for 6 GB (with partial GPU offload):
| Model | Source | Notes |
|-------|--------|-------|
| SD 1.5 | \`stabilityai/stable-diffusion-v1-5\` | Fast, huge LoRA library |
| SDXL Turbo | \`stabilityai/sdxl-turbo\` | 4-step, good quality |
| SDXL Base | \`stabilityai/stable-diffusion-xl-base-1.0\` | Best quality, slower |
| SD 2.1 | \`stabilityai/stable-diffusion-2-1\` | Good mid-size choice |
## Ollama — add more models
\`\`\`bash
# Pull any model while llm stack is running
docker exec ollama ollama pull llama3.2:3b
docker exec ollama ollama pull nomic-embed-text # RAG embeddings
docker exec ollama ollama list # see installed models
\`\`\`
Browse models at: https://ollama.com/library
For 6 GB cards, stick to 7B or smaller with Q4_K_M quantisation (~4.5 GB).
## Open WebUI — first login
Open http://localhost:3000 and create your admin account on first visit.
Models pulled into Ollama appear automatically in the model dropdown.
Enable web search: Settings → Admin → Web Search (SearXNG is pre-configured).
## Manage individual stacks
\`\`\`bash
cd $AI_DIR/image-gen && docker compose up -d # start InvokeAI
cd $AI_DIR/llm && docker compose up -d # start Ollama + OpenWebUI
cd $AI_DIR/portal && docker compose up -d # start portal
docker compose -f $AI_DIR/image-gen/docker-compose.yml logs -f invokeai
docker compose -f $AI_DIR/llm/docker-compose.yml logs -f openwebui
\`\`\`
## Update
\`\`\`bash
cd $REPO_DIR && git pull
cd $AI_DIR/image-gen && docker compose pull && docker compose up -d
cd $AI_DIR/llm && docker compose pull && docker compose up -d
cd $AI_DIR/portal && docker compose build --pull && docker compose up -d
\`\`\`
MD
# ── Start stacks + pull models ────────────────────────────────────────────
echo ""
log_info "What would you like to start now?"
log_info " 1) Portal only — start the swap controller, configure the rest later"
log_info " 2) Portal + LLM stack — start Ollama/OpenWebUI and pull selected models"
log_info " 3) Portal + image-gen — start InvokeAI and queue the starter model download"
log_info " 4) None — start manually later"
echo ""
local START_CHOICE=""
prompt_text "Choice [2]:" "2" START_CHOICE
# Always start portal if any stack is starting
if [[ "$START_CHOICE" =~ ^[123]$ ]]; then
docker compose -f "$PORTAL_DIR/docker-compose.yml" up -d \
&& log_success "Portal started — http://localhost:8080" \
|| log_warning "Portal start failed — check: docker compose -f $PORTAL_DIR/docker-compose.yml logs"
fi
if [[ "$START_CHOICE" == "2" ]]; then
# Start LLM stack
docker compose -f "$LLM_DIR/docker-compose.yml" up -d \
&& log_success "LLM stack started" \
|| { log_warning "LLM stack start failed"; START_CHOICE="0"; }
# Pull Ollama models if any were selected
if [ ${#OLLAMA_MODELS[@]} -gt 0 ] && [[ "$START_CHOICE" == "2" ]]; then
log_info "Waiting for Ollama to be ready..."
local _w=0
while ! curl -sf "http://localhost:11434/api/version" &>/dev/null; do
sleep 3; _w=$((_w+3))
[[ $_w -ge 90 ]] && { log_warning "Ollama not responding after 90s — pull models manually later"; break; }
done
if curl -sf "http://localhost:11434/api/version" &>/dev/null; then
for _m in "${OLLAMA_MODELS[@]}"; do
log_info "Pulling $_m (this may take a while)..."
docker exec ollama ollama pull "$_m" \
&& log_success "$_m ready" \
|| log_warning "Pull failed for $_m — retry: docker exec ollama ollama pull $_m"
done
log_success "Open WebUI ready at: http://localhost:3000"
log_info "Create your admin account on the first visit."
fi
fi
fi
if [[ "$START_CHOICE" == "3" ]]; then
# Start image-gen stack
docker compose -f "$IMAGE_GEN_DIR/docker-compose.yml" up -d \
&& log_success "InvokeAI started" \
|| { log_warning "InvokeAI start failed — check: docker compose -f $IMAGE_GEN_DIR/docker-compose.yml logs"; START_CHOICE="0"; }
# Queue starter model via InvokeAI REST API
if [ -n "$INVOKE_MODEL_SOURCE" ] && [[ "$START_CHOICE" == "3" ]]; then
log_info "Waiting for InvokeAI to be ready (model database initialises on first start)..."
local _w=0
while ! curl -sf "http://localhost:9090/api/v1/app/version" &>/dev/null; do
sleep 5; _w=$((_w+5))
[[ $_w -ge 180 ]] && { log_warning "InvokeAI not responding after 3 min"; break; }
done
if curl -sf "http://localhost:9090/api/v1/app/version" &>/dev/null; then
log_info "Queuing $INVOKE_MODEL_NAME download..."
local _resp
_resp=$(curl -s -X POST "http://localhost:9090/api/v2/models/install" \
-H "Content-Type: application/json" \
-d "{\"source\": \"${INVOKE_MODEL_SOURCE}\"}" 2>/dev/null)
if echo "$_resp" | grep -q '"id"'; then
log_success "$INVOKE_MODEL_NAME queued — downloading in background"
log_info "Track progress: http://localhost:9090 → Model Manager → In Progress"
else
log_warning "Could not queue via API. Install manually:"
log_info " Open http://localhost:9090 → Model Manager → Add Model"
log_info " Source: $INVOKE_MODEL_SOURCE"
fi
fi
fi
fi
if [[ "$START_CHOICE" == "4" ]] || [[ "$START_CHOICE" == "0" ]]; then
log_info "Start when ready:"
log_info " docker compose -f $PORTAL_DIR/docker-compose.yml up -d"
log_info " docker compose -f $LLM_DIR/docker-compose.yml up -d"
log_info " docker compose -f $IMAGE_GEN_DIR/docker-compose.yml up -d"
fi
echo ""
echo " Portal: http://localhost:8080 (GPU swap controller)"
echo " InvokeAI: http://localhost:9090 (image-gen stack)"
echo " Open WebUI: http://localhost:3000 (llm stack)"
echo " Ollama API: http://localhost:11434 (llm stack)"
echo " Source repo: $REPO_DIR"
echo ""
if [ ${#OLLAMA_MODELS[@]} -gt 0 ]; then
echo " Ollama models queued: ${OLLAMA_MODELS[*]}"
fi
if [ -n "$INVOKE_MODEL_NAME" ]; then
echo " InvokeAI starter: $INVOKE_MODEL_NAME ($INVOKE_MODEL_SOURCE)"
fi
echo ""
}
[[ "${_RUN_STANDALONE:-0}" == 1 ]] && install_ai_gpu
services/iopaint.sh
+475
View File
@@ -0,0 +1,475 @@
#!/bin/bash
# services/iopaint.sh — AI image editing: erase objects, fill regions, replace with text prompt.
# Part of the modular post-install system (sourced by setup.sh).
#
# Can also be run standalone on any machine:
# sudo bash iopaint.sh
# (Docker must already be installed when run standalone)
#
# Three use cases:
# Erase/remove — mask an object, AI fills the gap (LaMa, CPU-safe)
# Inpaint/fill — restore damaged areas, remove watermarks (multiple models)
# Replace — mask + text prompt → AI draws new content (PowerPaint, GPU required)
#
# IOPaint is local-only: it cannot call a remote GPU or InvokeAI on another machine.
# For text-guided replacement the GPU must be on this same machine.
# IOPaint has no built-in auth — protect with Authelia via Caddy.
# ── Standalone bootstrap ──────────────────────────────────────────────────────
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
[[ "$(id -u)" == "0" ]] || { echo "Run with sudo: sudo bash $0"; exit 1; }
_SELF_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
_COMMON="$_SELF_DIR/../lib/common.sh"
if [[ -f "$_COMMON" ]]; then
source "$_COMMON"
else
log_info() { echo -e "\033[0;34m[INFO]\033[0m $*"; }
log_success() { echo -e "\033[0;32m[OK]\033[0m $*"; }
log_warning() { echo -e "\033[1;33m[WARN]\033[0m $*"; }
log_error() { echo -e "\033[0;31m[ERROR]\033[0m $*" >&2; }
require_docker() {
command -v docker &>/dev/null || {
log_error "Docker not found. Install it first:"
log_error " curl -fsSL https://get.docker.com | sudo sh"
return 1
}
docker compose version &>/dev/null || {
log_error "Docker Compose plugin missing:"
log_error " sudo apt-get install -y docker-compose-plugin"
return 1
}
}
ensure_docker_dir_ownership() {
chown -R "$ACTUAL_USER:$ACTUAL_USER" "$@" 2>/dev/null || true
}
prompt_text() {
local _q="$1" _def="$2" _var="$3" _r
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
read -r -p " $_q " _r
eval "$_var='${_r:-$_def}'"
}
prompt_yn() {
local _q="$1" _def="$2" _var="$3" _r
[[ "${UNATTENDED:-false}" == "true" ]] && { eval "$_var='$_def'"; return; }
read -r -p " $_q " _r
eval "$_var='${_r:-$_def}'"
}
configure_caddy_for_service() {
local _name="$1" _upstream="$2" _subdomain="$3" _extra="${4:-}"
local _caddy_dir="$DOCKER_DIR/caddy"
local _caddyfile="$_caddy_dir/Caddyfile"
local _display_port="${_upstream##*:}"
local _mode="none"
[[ -d "$_caddy_dir" ]] && _mode="local"
[[ -n "${CADDY_REMOTE_HOST:-}" ]] && [[ "$_mode" != "local" ]] && _mode="remote"
[[ "$_mode" == "none" ]] && {
log_info "Access $_name directly on port $_display_port."
return 0
}
echo ""
local _do_caddy=""
if [[ "$_mode" == "remote" ]]; then
log_info "Remote Caddy configured (${CADDY_REMOTE_HOST})."
log_info "A snippet file will be saved to ~/docker/caddy-snippets/."
fi
read -r -p " Configure Caddy reverse proxy for $_name? [y/N]: " _do_caddy
[[ "${_do_caddy,,}" == "y" ]] || {
log_info "Skipping — access at: http://localhost:$_display_port"
return 0
}
local _default_domain=""
if [[ -n "${SITE_DOMAIN:-}" ]] && [[ "$SITE_DOMAIN" != "example.com" ]]; then
_default_domain="${_subdomain}.${SITE_DOMAIN}"
log_info "Default: $_default_domain"
fi
local _domain=""
read -r -p " Domain [${_default_domain:-required}]: " _domain
_domain="${_domain:-$_default_domain}"
[[ -n "$_domain" ]] || { log_warning "No domain entered — skipping Caddy."; return 0; }
local _block_upstream="$_upstream"
if [[ "$_mode" == "remote" ]]; then
_block_upstream="${CADDY_REMOTE_HOST}:${_display_port}"
fi
local _site_block
_site_block="$(cat << CBLOCK
# $_name
${_domain} {
reverse_proxy ${_block_upstream}
header {
Strict-Transport-Security "max-age=31536000; includeSubDomains; preload"
X-Content-Type-Options "nosniff"
X-Frame-Options "SAMEORIGIN"
Referrer-Policy "strict-origin-when-cross-origin"
}
log {
output file /var/log/caddy/${_domain}.log
format json
}
${_extra}
}
CBLOCK
)"
if [[ "$_mode" == "local" ]]; then
if [[ -f "$_caddyfile" ]]; then
local _bk="$_caddy_dir/Caddyfile.backup.$(date +%Y%m%d-%H%M%S)"
cp "$_caddyfile" "$_bk"
log_info "Backed up Caddyfile to $(basename "$_bk")"
else
touch "$_caddyfile"
fi
if grep -q "^${_domain}" "$_caddyfile" 2>/dev/null; then
log_warning "$_domain already in Caddyfile"
local _ow=""
read -r -p " Overwrite? [y/N]: " _ow
[[ "${_ow,,}" == "y" ]] || { log_info "Keeping existing entry."; return 0; }
sed -i "/^${_domain}/,/^}/d" "$_caddyfile"
fi
printf '%s\n' "$_site_block" >> "$_caddyfile"
log_success "Added $_domain to Caddyfile"
docker exec caddy caddy fmt --overwrite /etc/caddy/Caddyfile 2>/dev/null || true
if docker exec caddy caddy reload --config /etc/caddy/Caddyfile 2>/dev/null; then
log_success "$_name accessible at: https://$_domain"
else
log_warning "Reload failed — check: docker logs caddy"
log_info "Manual reload: docker exec caddy caddy reload --config /etc/caddy/Caddyfile"
fi
else
local _snippet_dir="$DOCKER_DIR/caddy-snippets"
local _snippet_file="$_snippet_dir/${_subdomain}.caddy"
mkdir -p "$_snippet_dir"
printf '%s\n' "$_site_block" > "$_snippet_file"
chown "$ACTUAL_USER:$ACTUAL_USER" "$_snippet_file" 2>/dev/null || true
log_success "Snippet saved: $_snippet_file"
log_info "Copy to Caddy machine:"
log_info " scp $_snippet_file caddy-host:~/caddy-snippets/"
log_info " rsync -av $_snippet_dir/ caddy-host:~/caddy-snippets/ (all at once)"
fi
}
write_readme() {
local _dir="$1"
mkdir -p "$_dir"
[[ "${DRY_RUN:-false}" == "true" ]] && return 0
cat > "$_dir/README.md"
}
fi
ACTUAL_USER="${ACTUAL_USER:-${SUDO_USER:-$USER}}"
ACTUAL_HOME="$(getent passwd "$ACTUAL_USER" 2>/dev/null | cut -d: -f6 || echo "${HOME:-/root}")"
DOCKER_DIR="${DOCKER_DIR:-$ACTUAL_HOME/docker}"
DRY_RUN="${DRY_RUN:-false}"
UNATTENDED="${UNATTENDED:-false}"
SITE_TZ="${SITE_TZ:-$(cat /etc/timezone 2>/dev/null || echo UTC)}"
SITE_DOMAIN="${SITE_DOMAIN:-example.com}"
SITE_CADDY_NET="${SITE_CADDY_NET:-caddy_net}"
CADDY_REMOTE_HOST="${CADDY_REMOTE_HOST:-}"
register_service() { :; }
_RUN_STANDALONE=1
fi
# ─────────────────────────────────────────────────────────────────────────────
register_service iopaint utilities "AI image inpainting — erase objects, fill, restore (IOPaint)" 8100
install_iopaint() {
require_docker || return 1
log_info "Installing IOPaint..."
local IOPAINT_DIR="$DOCKER_DIR/iopaint"
if [ "$DRY_RUN" = true ]; then
echo "[DRY-RUN] Would create $IOPAINT_DIR"
echo "[DRY-RUN] Would prompt for model and GPU (CUDA) support"
echo "[DRY-RUN] Would write docker-compose.yml and .env"
echo "[DRY-RUN] Would offer Authelia SSO"
return 0
fi
mkdir -p "$IOPAINT_DIR"
ensure_docker_dir_ownership "$IOPAINT_DIR"
cd "$IOPAINT_DIR" || return 1
# ── GPU ──────────────────────────────────────────────────────────────────
log_info "IOPaint can:"
log_info " • Erase / remove — mask an object, AI fills the gap (works CPU-only)"
log_info " • Inpaint / fill — restore damaged areas, remove watermarks"
log_info " • Replace — mask + type what goes there → AI draws it (needs GPU)"
log_info " Note: inference is always local — IOPaint cannot use a GPU on another machine."
echo ""
local USE_GPU=""
prompt_yn "Enable CUDA GPU support? Requires nvidia-container-toolkit (y/n):" "n" USE_GPU
# ── Model selection ───────────────────────────────────────────────────────
echo ""
log_info "Select default model (you can switch models in the UI without restarting):"
echo ""
log_info " ── CPU-safe — work on any machine ─────────────────────────────────────────"
log_info " 1) lama Erase / removal. Intelligent gap fill. ~200 MB ← Recommended"
log_info " 2) cv2 OpenCV fill. No download, instant. Rough quality."
log_info " 3) zits Portrait & face restoration. ~200 MB."
log_info " 4) manga Comic/manga text bubble removal. ~100 MB."
echo ""
if [[ "$USE_GPU" =~ ^[Yy]$ ]]; then
log_info " ── GPU-accelerated fill ───────────────────────────────────────────────────"
log_info " 5) migan MiGAN: fast GPU inpainting. ~50 MB."
log_info " 6) fcf FcF: high-quality contextual fill. ~600 MB."
log_info " 7) mat MAT: large missing region fill. ~300 MB."
log_info " 8) ldm LDM: latent diffusion texture fill. ~1.2 GB."
echo ""
log_info " ── Text-guided REPLACEMENT (GPU + Stable Diffusion) ───────────────────────"
log_info " 9) Sanster/PowerPaint-V2-filling"
log_info " Mask + type 'a red barn' → AI draws it. ~4 GB."
log_info " Modes: text-guided, shape-guided, erase, outpaint."
log_info " 10) runwayml/stable-diffusion-inpainting"
log_info " Classic SD 1.5 inpaint. Huge LoRA/style library. ~4 GB."
echo ""
fi
local MODEL_NUM=""
prompt_text "Model choice [1=lama]:" "1" MODEL_NUM
local IOPAINT_MODEL="lama"
case "$MODEL_NUM" in
2) IOPAINT_MODEL="cv2" ;;
3) IOPAINT_MODEL="zits" ;;
4) IOPAINT_MODEL="manga" ;;
5) IOPAINT_MODEL="migan" ;;
6) IOPAINT_MODEL="fcf" ;;
7) IOPAINT_MODEL="mat" ;;
8) IOPAINT_MODEL="ldm" ;;
9) IOPAINT_MODEL="Sanster/PowerPaint-V2-filling" ;;
10) IOPAINT_MODEL="runwayml/stable-diffusion-inpainting" ;;
*) IOPAINT_MODEL="lama" ;;
esac
local DEVICE_VAL="cpu"
[[ "$USE_GPU" =~ ^[Yy]$ ]] && DEVICE_VAL="cuda"
# ── docker-compose.yml ────────────────────────────────────────────────────
# MODEL and DEVICE come from .env — change them there and restart to switch.
# Volume ./models:/root/.cache persists ALL model caches:
# /root/.cache/torch/hub/checkpoints/ (LaMa, CV2, ZITS, etc.)
# /root/.cache/huggingface/ (SD, PowerPaint, LDM, etc.)
if [[ "$USE_GPU" =~ ^[Yy]$ ]]; then
cat > docker-compose.yml << 'IOPAINT_GPU'
name: iopaint
services:
iopaint:
image: cwq1913/iopaint:latest
container_name: iopaint
hostname: iopaint
restart: unless-stopped
command: >-
iopaint start
--model=${MODEL:-lama}
--device=${DEVICE:-cuda}
--port=8080
--host=0.0.0.0
ports:
- "8100:8080"
env_file: .env
volumes:
- ./models:/root/.cache
- ./input:/app/input
- ./output:/app/output
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
networks:
- caddy_net
networks:
caddy_net:
external: true
name: ${CADDY_NET:-caddy_net}
IOPAINT_GPU
else
cat > docker-compose.yml << 'IOPAINT_CPU'
name: iopaint
services:
iopaint:
image: cwq1913/iopaint:latest
container_name: iopaint
hostname: iopaint
restart: unless-stopped
command: >-
iopaint start
--model=${MODEL:-lama}
--device=${DEVICE:-cpu}
--port=8080
--host=0.0.0.0
ports:
- "8100:8080"
env_file: .env
volumes:
- ./models:/root/.cache
- ./input:/app/input
- ./output:/app/output
networks:
- caddy_net
networks:
caddy_net:
external: true
name: ${CADDY_NET:-caddy_net}
IOPAINT_CPU
fi
# ── .env ─────────────────────────────────────────────────────────────────
cat > .env << IOPAINT_ENV
# IOPaint — change MODEL and restart to switch (no need to edit docker-compose.yml)
# Current model (set during install — see README for full model list)
MODEL=${IOPAINT_MODEL}
# Device: cpu or cuda
# For GPU: also requires the deploy: block in docker-compose.yml
DEVICE=${DEVICE_VAL}
# Caddy network
CADDY_NET=${SITE_CADDY_NET}
IOPAINT_ENV
chmod 600 .env
mkdir -p models input output
chown -R "$ACTUAL_USER:$ACTUAL_USER" "$IOPAINT_DIR"
echo ""
log_success "IOPaint configured — model: $IOPAINT_MODEL | device: $DEVICE_VAL"
if [[ "$IOPAINT_MODEL" == *"PowerPaint"* ]] || [[ "$IOPAINT_MODEL" == *"stable-diffusion"* ]]; then
log_info "SD-based model selected (~4 GB). It downloads from HuggingFace on first start."
log_info "If the download fails, try: HF_TOKEN=your_token docker compose up -d"
else
log_info "Model downloads automatically on first start (LaMa ~200 MB)."
fi
log_info "Switch models any time by editing MODEL= in .env and restarting."
# No built-in auth — offer Authelia SSO protection
local EXTRA_BLOCK=""
if [ -d "$DOCKER_DIR/authelia" ]; then
local _use_auth=""
prompt_yn "Protect IOPaint with Authelia SSO? (y/n):" "y" _use_auth
[[ "$_use_auth" =~ ^[Yy]$ ]] && EXTRA_BLOCK=" import authelia"
fi
configure_caddy_for_service "IOPaint" "iopaint:8080" "inpaint" "$EXTRA_BLOCK"
write_readme "$IOPAINT_DIR" << 'MD'
# IOPaint
AI-powered image editing:
- **Erase / remove** — mask an object, AI fills the background (LaMa, works CPU-only)
- **Inpaint / restore** — fix damaged areas, remove watermarks
- **Replace with AI** — mask something + type what goes there → AI draws it (PowerPaint, GPU)
Note: IOPaint is **local only** — all inference runs on this machine.
For text-guided replacement a CUDA GPU on this machine is required.
## Access
- URL: http://localhost:8100
- No built-in login — protect via Authelia SSO if exposed
## Switching models
Edit `MODEL=` in `.env` and restart — no need to touch `docker-compose.yml`:
```bash
cd ~/docker/iopaint
nano .env # change MODEL= line
docker compose restart
```
## Model reference
| # | Model | Type | Size | Best for |
|---|-------|------|------|---------|
| 1 | `lama` | CPU-safe | ~200 MB | **Object erase/removal** (default) |
| 2 | `cv2` | CPU-safe | built-in | Basic fill, no download |
| 3 | `zits` | CPU-safe | ~200 MB | Portrait & face restoration |
| 4 | `manga` | CPU-safe | ~100 MB | Comic/manga text bubble removal |
| 5 | `migan` | GPU | ~50 MB | Fast GPU inpainting |
| 6 | `fcf` | GPU | ~600 MB | High-quality contextual fill |
| 7 | `mat` | GPU | ~300 MB | Large missing region fill |
| 8 | `ldm` | GPU | ~1.2 GB | Latent diffusion texture fill |
| 9 | `Sanster/PowerPaint-V2-filling` | GPU+SD | ~4 GB | **Text-guided replacement** |
| 10 | `runwayml/stable-diffusion-inpainting` | GPU+SD | ~4 GB | SD 1.5 inpaint, large LoRA library |
SD-based models (9, 10) download from HuggingFace on first start.
If a gated model needs a token: add `HF_TOKEN=xxx` to `.env`.
## How to use
1. Open http://localhost:8100
2. Upload an image (or drag & drop)
3. Paint a mask over the area to change
4. For erase models: click Run → gap fills automatically
5. For SD models (PowerPaint): type a text prompt → AI draws it into the masked area
## GPU acceleration
Requires `nvidia-container-toolkit`. The GPU compose adds a `deploy:` block.
Re-run the installer with GPU=y to regenerate docker-compose.yml, or manually add:
```yaml
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
```
Then change `DEVICE=cuda` in `.env` and restart.
## Manage
```bash
cd ~/docker/iopaint
docker compose up -d
docker compose down
docker compose logs -f
docker compose pull && docker compose down && docker compose up -d
```
## Files
- docker-compose.yml — stack (MODEL and DEVICE come from .env)
- .env — model and device config
- models/ — all cached model weights (torch + HuggingFace)
- input/, output/ — optional file staging
MD
local START_IO=""
prompt_yn "Start IOPaint now? (y/n):" "y" START_IO
if [ "$START_IO" = "y" ] || [ "$START_IO" = "Y" ]; then
docker compose up -d \
&& log_success "IOPaint started — model downloads on first use" \
|| log_warning "Start failed — check: docker compose logs"
fi
echo ""
echo " URL: http://localhost:8100"
echo " Model: $IOPAINT_MODEL"
echo " Device: $DEVICE_VAL"
echo " Switch: edit MODEL= in $IOPAINT_DIR/.env and restart"
echo ""
}
[[ "${_RUN_STANDALONE:-0}" == 1 ]] && install_iopaint