Prompt LibraryPrompt Library / Cinematic Establishing Shot / for HunyuanImage
Cinematic Establishing Shot Prompt for HunyuanImage
This is the HunyuanImage version of the cinematic establishing shot prompt: a wide opening frame that establishes place, time and mood before any subject appears — the first shot of a sequence. It is formatted the way HunyuanImage 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 establishing image, 21:9, that reads as a location in a single glance: foreground element, midground subject ground, and background depth all present. Acceptance check: a viewer who has never seen the project can name the place type, the time of day and the mood in one sentence; no person is close enough to camera to become the subject.
Series: YouTube Production — Step 1 of 3 — the opener. See its place in the full workflow
Using this prompt with HunyuanImage
HunyuanImage (Tencent, current 3.0 line) is an open-weights multimodal model that rewards long, complete descriptive prose: it reasons about the prompt with world knowledge, so state the scene fully — subject, environment, era, materials, light — in sentences rather than tags. It also edits images in the same conversation style: supply the reference image and describe what changes. The weights are large (an 80B MoE family) and run on multi-GPU local setups or Tencent's hosted surfaces.
What this route costs — and how to pay less
Cost structure: open weights — HunyuanImage runs on your own hardware (a multi-GPU setup for the full model), so the marginal cost per generation is zero; Tencent's hosted surfaces are the alternative. 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 — [LOCATION], [TIME OF DAY], [FOREGROUND ELEMENT], [WEATHER OR ATMOSPHERE] — 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 HunyuanImage or any other model.
More HunyuanImage prompts
Mpromp2 — the AI Prompt Generator. Every prompt in this library is free to use, including commercially.