Invokeai
App in the BluixApps catalog
What it is
InvokeAI is an enterprise-grade Stable Diffusion UI — built by Invoke Inc. (commercial company) but with a fully open-source core. Where A1111 is the community workshop and ComfyUI is the graph editor, InvokeAI is the professional canvas designed for studios that need a managed, multi-user, production-grade SD setup.
Think Photoshop for AI image generation.
What it's for
- Unified Canvas — paint on a canvas, AI fills in (layered editing with masking)
- Workflows tab — node-graph (similar to ComfyUI but inside the studio app)
- Queue Manager — batch jobs visible, prioritizable
- Models Library — install/manage SD checkpoints with metadata
- Multi-user — accounts system for studio teams
- Boards — organize outputs into named projects
- Image history — never lose a generation, full prompt + settings preserved
Who it's for
- Professional studios producing AI art commercially
- Creative agencies with multiple team members sharing a SD setup
- Designers who want Photoshop-like canvas workflows for AI
- Enterprises evaluating self-hosted SD for compliance reasons
- Hosting providers selling managed SD to design studios
Why teams pick InvokeAI over alternatives
- Apache 2.0 — fully open, commercial-friendly
- Best canvas experience — A1111's inpainting feels primitive in comparison
- Production-grade UX — designed for daily professional use
- Multi-user out of box — accounts, boards, per-user settings
- Active commercial backing — Invoke Inc. funds development
- Model Manager — visual model install/uninstall (no command line)
- Settings persistence — UI state restored across sessions
Integrations
- ControlNet — full preprocessor + model support
- LoRA management — drag-drop install + auto-detect triggers
- HF model search — install from HuggingFace inside UI
- CivitAI — direct download integration
- Workflows API — REST endpoints for automation
- Reverse proxy — HTTPS + auth recommended for production
- OIDC — auth via external IdP (planned/community)
- Multi-GPU — assign workflows to specific GPUs
Notable users & community
- 27k+ GitHub stars
- Commercial backing (Invoke Inc., Y Combinator W23)
- Used by professional studios, ad agencies, game studios
- Active Discord with 20k+ members
- Distinct product positioning vs A1111 (professional vs hacker)
Tips & operations
- Resource planning: 8GB VRAM minimum, 12-16GB for SDXL canvas work
- Model Manager: install models from URL or HF directly in UI
- Boards: organize per-project, easy to find historical generations
- Workflows: build once, save, batch-execute
- Persistent root:
/invokeaimount preserves all state - Multi-user: configure
invokeai.yamlfor production deployments - Backups: postgres-free architecture (uses SQLite) — backup = copy
/invokeai/databases
What we ship in BluixApps
- Docker (ghcr.io/invoke-ai/invokeai:latest) with NVIDIA runtime
- INVOKEAI_ROOT mounted to
/opt/invokeaipersistent host volume - Port 9090 mapped,
--host 0.0.0.0configured - Install report at
/root/bluixapps/invokeai.txt - Production hardening (auth, reverse proxy, HTTPS) documented
- Backup hook covers models + outputs + databases + boards
- GPU pre-flight check via
bluixapps_ensure_nvidia_runtime
Get this app — pick a BluixApps plan
Same catalog. Scaling tenant isolation, white-label and support tier.
| Tier | Tenants | Catalog | Support | White-label | Monthly | |
|---|---|---|---|---|---|---|
| Stacks | 1 | 19 curated stacks | Standard | — | $19/mo | DetailDeploy |
| Starter | 10 | Full catalog | Standard | +$15–25/mo | $49/mo | DetailDeploy |
| Pro | 25 | Full catalog | Priority bugfix | +$15–25/mo | $149/mo | DetailDeploy |
| Growth | 100 | Full catalog | Priority bugfix | +$15–25/mo | $349/mo | DetailDeploy |
| Scale | 500 | Full catalog | 7-day window | +$15–25/mo | $799/mo | DetailDeploy |
| Enterprise | Unlimited | Full catalog | Priority 7-day | Bundled | $1,499/mo | DetailDeploy |