Prompt LibraryPrompt Library / B-Roll Footage Generator / for HunyuanVideo
B-Roll Footage Generator Prompt for HunyuanVideo
This is the HunyuanVideo version of the b-roll footage generator prompt: clean, narration-ready B-roll: one subject, one gliding camera move, nothing that fights a voiceover or an edit. It is formatted the way HunyuanVideo takes prompts best. Free — copy it, replace the bracketed parts, and paste it in.
The prompt
Push copies this prompt with a reference line naming your image, and downloads the image file — attach it in the model to complete the pair. This page stages the pair for you; it cannot upload into the model itself (sites cannot reach into each other), so the final attach happens there. The image is downscaled to at most 1024px and stored only in this browser, paired with this prompt. If browser storage is full, it is kept for this visit only.
The deliverable — and how to check it
Deliverable: one 8-second clip with a single continuous camera move and no cuts, subject in frame for the full duration, clean head and tail (at least 1 second of settled frame at each end for edit points). Acceptance check: the clip must sit under narration without any moment that pulls attention — no faces to camera, no text, no sudden movement.
Series: YouTube Production — Step 2 of 3 — supporting footage. See its place in the full workflow
Using this prompt with HunyuanVideo
HunyuanVideo (Tencent, current 1.5 line) is an open-weights video model that rewards detailed descriptive prose — the longer and more complete the shot description, the better it follows. It does both text-to-video and image-to-video, so a keyframe can anchor the shot. It generates no native audio (Tencent pairs it with a separate sound model) — plan the soundtrack separately. At 8.3B parameters it runs on consumer-grade GPUs locally, unusually light for its quality class.
What this route costs — and how to pay less
Cost structure: open weights — HunyuanVideo runs on your own hardware (consumer-grade GPUs suffice for the 1.5 line), so the marginal cost per generation is zero. The same prompt is pre-configured in this library for every major model, so you can run it on whichever route fits your budget — comparing the structures before you generate is a free way to save money.
Replace the bracketed placeholders — [SUBJECT OR PROCESS], [SETTING], [LIGHT] — with your own details before pasting.
Other versions and customization
See all model versions of this prompt, or open the prompt gateway to build a custom prompt from your own one-line goal, formatted for HunyuanVideo or any other model.
More HunyuanVideo prompts
Mpromp2 — the AI Prompt Generator. Every prompt in this library is free to use, including commercially.