Launching Mid-May 2026

What do you
imagine?

Local AI that directs real 3D cinematic video. Not generated pixels — real Blender rendering, on your machine. Yours forever.

// no cloud. no credits. no limits.

Building in public · follow on GitHub
15
Recipes
300+
Curated Assets
4
Render Tiers
Renders / Mo
fantasy-studio — polar bear cinematic render
90 seconds — type prompt, get cinematic render, no cloud.
A guided tour of
the studio.
Type a prompt, AI directs, Blender renders — all local, all yours. Here's the full UI.
Fantasy Studio main canvas
Step 01

The Studio

Your canvas. Type any scene. The director plans casting, camera, lighting, and pacing.

Render tier selector
Step 02

AI Direction

Pick rendering quality. Iterate fast in Quick Preview, then commit to a Final Cinematic hero render.

Cast panel — pick or swap assets
Step 03

Cast Anything

AI auto-picks. You can override. 300+ curated assets, healed and ground-aligned, ready to render.

Scene controls
Step 04

Direct Every Detail

Lighting presets, camera modes, duration, brand color, template selection — all controllable.

Refine panel
Step 05

Refine With Words

"Lower the camera." "Switch to golden hour." "More dramatic." Talk to the director — the scene iterates.

Built like a
cinematic brain.
Every layer — from local AI direction to Cycles ray-tracing — engineered to produce studio-quality output from a single prompt.
🎬

Cycles Ray Tracing

Photorealistic path-traced rendering. Not AI hallucinated pixels — real light simulation with global illumination, caustics, and volumetrics.

🧠

AI Director (Local LLM)

A local Gemma 3 12B (via Ollama) plans every creative decision — camera, lighting, atmosphere, animation. Falls back to a deterministic director if the LLM is unavailable.

💻

100% Local Execution

Your GPU. Your renders. Your data. Zero cloud dependencies. No credits. No throttling. No subscription required to render.

📚

Curated Library + Smart Fallback

300+ healed assets ready to render. Don't have what you need? The agent searches Objaverse (798K+ open assets) and Sketchfab as fallbacks. Auto-fetched quality varies — that's why curated assets ship with the product.

💬

Refine With Words

After your first render, adjust the scene with natural language. "Lower the camera." "Switch to golden hour." "More dramatic." The director iterates without starting over.

📦

Real Exports

MP4 video, animated GIF, PNG sequence, and the source .blend file. Re-light, re-frame, re-render in Blender forever.

Inside the AI.
Real engineering, not magic. Four AI subsystems direct every render — each hand-tuned, each debuggable, each running on your machine.
subsystem · 01

Scene Director

Local Gemma 3 12B via Ollama plans every scene. Picks camera, lighting, mood, and pacing from a one-line prompt. Falls back to a deterministic rule-based director when the LLM is unavailable, so renders never block on inference.

model: gemma3:12b · runtime: ollama · fallback: deterministic
subsystem · 02

Asset Resolver

Reads your prompt and searches the curated library first (alias-mapped for plurals + synonyms). Falls back to Objaverse (798K+ assets) for unusual subjects, then Sketchfab. All running on your machine — no asset metadata leaves the box.

curated: 300+ · fallback: Objaverse · then: Sketchfab
subsystem · 03

Recipe Dispatcher

15 cinematic recipes compete for every prompt. The dispatcher scores each against the planned scene — subject_type match, environment match, dispatch keyword overlap. The best directorial style wins. Each recipe is hand-tuned by humans, not generated by AI.

recipes: 15 + _default · scoring: weighted overlap
subsystem · 04

Verification Gates

Every render runs seven structural checks before frames hit disk: bbox sanity, frustum, framing fill, primitive detection, orientation, grounding, hero tag. Bad outputs caught and aborted with a structured error — not silently shipped to you.

checks: 7 · abort: bbox_sane · oriented_correctly
From prompt to
production.
01

Prompt

Type anything. "Ferrari on a mountain road at golden hour."

02

AI Director

Local LLM plans the scene — assets, camera, lighting, mood, animation.

03

Asset Agent

Resolves 3D models and HDRIs. Downloads what's missing from free libraries.

04

Blender Render

Cycles renders. Compositor adds bloom, grade, atmosphere. MP4 + .blend out.

Not another
AI video tool.
AI Video GenWeb 3D ToolsFantasy Studio
Render qualityAI hallucinationsReal-time WebGPUCycles ray-traced (real light)
DeterministicNoYesYes
Runs locallyNoNoYes
Usage limitsCreditsCreditsUnlimited
Camera controlMinimalSomeCinematic
Export .blend sourceYes
Output tierConsumerWeb prototypeStudio CGI
Best for: single-subject cinematic shots (V1). Multi-subject composition is V2 work.
Live status.
Being built right now, in real time, on real GitHub. These tiles update from the public API.
GitHub stars
github.com/bgrut/fantasy-studio
Latest commit
checking…
Open issues
tracking the V1 polish list
Public source release
days · Mid-May 2026
Where we're going.
Honest about timeline being aspirational. Single-subject quality compounds — we ship Now and Next before getting clever.
Now
Mid-May 2026

V1 launch.

  • Single-subject cinematic shots
  • Public source release (BSL 1.1)
  • Polar bear / ferrari / horse renders working
  • 15 recipes, 4 render tiers
  • MP4 + .blend export
Soon
V1.5 – V1.9 · 3–6 months

Capability spread.

  • Cloud render tier (BYO-GPU optional)
  • Sound effects + ambient audio
  • Voice prompt input
  • Sharing / portfolio features
  • Patreon-only premium templates
Future
V2.0+ · 6–12 months

The hard stuff.

  • Marketplace launch (creator revenue share)
  • Multi-subject scene composition
  • Character consistency across scenes
  • Unreal Engine renderer backend
  • AI Director v2 — treatment → casting → blocking
// timelines aspirational · dependent on traction · feedback shapes priority

Follow the build

Ready to direct?

Join the waitlist. Be the first to turn prompts into cinematic reality.