~$HUNY
Tencent's open-source video generation model. Exceptional temporal coherence and motion fidelity. Industry-leading realism at 26GB VRAM.
Cold start comparison vs similar models. Lower is better.
No subscriptions. Buy credits, pay per inference. Scale to zero when idle.
import cumulus from "cumulus-sdk" // Deploy HunyuanVideo on Ion const client = await cumulus.deploy("hunyuanvideo") // Run inference const result = await client.run({ prompt: "Your prompt here", // model-specific params... })