H3, held still.
Create a finished frame.

Use H3’s visual world model as a high-detail text-to-image engine, with a short hidden temporal packet distilled into one selected still.

Describe the finished imageDescribe a final still—composition, light, material, lens, and style. Motion instructions are unnecessary.

CanvasRecipe

Measured GPU-time billing · $0.25 current estimate12-step default · native ~0.98 MP cap

REAL H3 EXAMPLE

Real H3 generationClassifier-verified example output

Classifier-routedEvery source and output is classified; adult inputs use the compatible H3 lane and adult outputs stay out of public search.

Shared model residencyText-to-image shares FL2VA, Qwen, and VAE weights with video. REF2VA is loaded only when editing needs it.

Measured, then drainedFinal price follows actual execution; the RunPod endpoint scales back to zero after its queue empties.

H3, held still.Create a finished frame.