img-forge · the image pipeline in every Stackbilder plan
Ship image assets
like you ship code.
One endpoint routes 11 models — 4-second SDXL drafts to Gemini ultra. Seed-locked character consistency, surgical inpainting, flat credits, and MCP tools your agents call unattended. Built for production pipelines, proven on our own.
“floor-to-ceiling office windows at golden hour, empty standing desk silhouetted against the city below, warm and cool light split, editorial architectural photography”
FLUX 2 Klein 4B
Black Forest Labs
FLUX 2 Klein 9B
Black Forest Labs
FLUX 1 Schnell
Black Forest Labs
Lucid Origin
Leonardo
Phoenix 1.0
Leonardo
SDXL Lightning
ByteDance
DreamShaper 8
Lykon
SDXL Base 1.0
Stability AI
One prompt · eight models · unedited API output. Pin any model per request, or let the quality tier route it.
Production proof
One game. 67 assets.
One visual universe.
The Tarot Detective is a live detective game whose entire art pipeline runs on img-forge — 16 portraits, 23 locations, 28 props. Every character keeps the same face across every scene: once a look is approved, every subsequent call reuses the same seed, so asset 43 still matches asset 2.
Built for agents and apps
One request. One URL back.
REST API and MCP tools. POST a prompt, get an asset_url. Your agent doesn't need to know which model is running — or ask a human to top up its balance.
# Generate — standard tier (default)
curl -X POST https://imgforge.stackbilt.dev/v2/generate \
-H "Authorization: Bearer sb_live_..." \
-d '{ "prompt": "a red fox in a snowy forest, golden hour" }'
# Response
{
"state": "completed",
"asset_url": "/v2/assets/7082f9..."
}
# Pin a specific model per request
-d '{ "prompt": "...", "cf_model": "@cf/leonardo/phoenix-1.0" }'11 models, one auth
SDXL, FLUX, Leonardo, and Gemini behind one token and one billing surface. Switch tiers per request — no per-provider accounts, no integration rewrite.
Generate, edit, correct
img2img restyling and mask-based inpainting through the same endpoint. Asset 43 of 67 has a bad hand? Fix the region, keep everything else — no re-roll, no drift from the approved look.
Your agent can pay its own bills
billing_status and billing_purchase_credits are MCP tools — an agent checks its balance mid-run, tops up, and keeps generating. Replicate, fal.ai, and Leonardo expose nothing like this to agents.
Pricing
Flat credits. No token math. No surprises.
Every model's exact cost, before you spend a credit. Caps pause — they never bill overage.
Free
Get started, no strings
- ✓5 images / month
- ✓All 9 Cloudflare-hosted models
- ✓3 governed scaffolds / month
- ✓REST API + MCP access
Pro
The whole platform, one price
- ✓1,000 img-forge credits / month
- ✓All tiers, Ultra and Ultra+ included
- ✓Unlimited scaffolds + LLM polish
- ✓Credit packs stack on top
- ✓Priority support
Agency
For production pipelines at volume
- ✓4,000 credits / month
- ✓Credits roll over while active
- ✓~8 full production runs / month
- ✓Priority queue + dedicated support
Need one-time volume? Builder and Studio credit packs never expire · full plan comparison
Production hardening for AI-generated software
Turn AI-generated apps into
production-ready software.
Vibe coding gets you a demo. Stackbilder generates governed scaffolds, threat models, ADRs, and test plans — before your prototype becomes production debt.
What ships with your code
Every scaffold includes governance. Automatically.
T-001: Spoofing — JWT validation bypass via alg:none
T-002: Tampering — D1 SQL injection in query builder
Severity: HIGH | Mitigation: parameterized queries...
Use cookie-based sessions over stateless JWTs.
Context: Edge runtime + D1 session store available...
test_auth_flow: login → session → protected route
test_billing: checkout → webhook → tier upgrade
Coverage target: 85% | Framework: vitest...
Security threat analysis
STRIDE-based threat modeling for your specific architecture. Identifies injection vectors, auth weaknesses, and data exposure risks before you write a line of code.
Architectural decision records
Every non-obvious choice documented with context, alternatives considered, and consequences. Your future self (and your team) will thank you.
Test plans
Integration and unit test specifications derived from your architecture. Coverage targets, frameworks, and specific scenarios — ready to implement.
Two-phase generation
Phase 1 is deterministic — same input, same output, zero inference cost, free tier. Phase 2 adds LLM polish that works within your architecture's constraints, not around them. How it works →
Start shipping images today.
Free tier includes 5 images and 3 scaffolds. No credit card. No tokens to buy.
Or get launch updates — no spam, just milestones.