Describe a scene; an agent assembles it.
VLM director plans a sequence of skill invocations — KitbashConductor for assets, SceneStager for lighting, TopoDoctor for repair, HolyGrail for quad cleanup — then the orchestrator dispatches them in parallel and stitches USD prims into one scene graph. Output branches to digital UE5, physical 3D print, or latent HDR backdrop.
$49 · BETA · TIER III
Prose in. The VLM director writes a small plan: which skills to call, in what order, with what arguments. The orchestrator dispatches them, the results merge into a USD scene graph. Output branches into the three modalities from the Hybrid 3D × AI workflow.
This tool is one node in a larger workflow: a hybrid 3D × AI film pipeline where image-driven generation, virtual cinematography, and physical 3D-printed mini-bigatures all share one USD substrate. Scene Stager drives lighting and camera physics from reference images. Kitbash Conductor browses asset libraries by shape. Topo Doctor enforces interchange-grade meshes between every stage. HolyGrail produces clean quad topology from triangulated booleans. Scene Composer orchestrates them all from prose prompts.
Sequencer · EXR · ProRes. UE5 Symmetry/PCG widgets. Tracked camera + 3D-stage match. RED-VRAPTOR 8K VV virtual cinematography.
Same USD asset, printed at scale (1 uu = 1 cm). HDR dome / LED stage backdrop. Camera match. In-camera weight.
Diffusion-extended infinity backdrops trained on the scene's motif corpus. Non-linear feedback loop into ideation.
Sketch → photoreal → curate → custom LDM → image→3D → ZBrush sculpt → Maya retopo → USD interchange → UE5 assembly → variant generation → branch to digital / physical / latent. The eleven-step pipeline that ties every ZForge AI-tier tool together.
Read the workflow PDF →