Mpromp2 — the AI Prompt GeneratorTheme

Prompt Library / Prompts for HunyuanImage

Free Prompts for HunyuanImage

This page collects every prompt in the library in its HunyuanImage version — each one formatted the way HunyuanImage takes prompts best, on its own page, all free. 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.

A finished product hero image — the kind of frame these prompts produce in this modelCinematics for HunyuanImageEvery cinematics prompt, pre-written for HunyuanImage — pick the outcome; the prompt is already written.

Image

Image & Video

Character Keyframe Consistency Workflow — the frame this prompt producesCharacter Keyframe Consistency Workflow for HunyuanImageLock one character's face, hair and wardrobe into a reusable keyframe sheet, so every later image and video generation can be matched against it.Product Ad Hero Shot — the frame this prompt producesProduct Ad Hero Shot for HunyuanImageA commercial hero image of a product with deliberate negative space reserved for ad copy.Cinematic Establishing Shot — the frame this prompt producesCinematic Establishing Shot for HunyuanImageA wide opening frame that establishes place, time and mood before any subject appears — the first shot of a sequence.Storyboard Sequence Sheet — the frame this prompt producesStoryboard Sequence Sheet for HunyuanImageA six-panel storyboard of one scene with the same character throughout — the planning frame a whole video sequence is built from.Portrait Consistency Set (Same Person, Three Expressions) — the frame this prompt producesPortrait Consistency Set (Same Person, Three Expressions) for HunyuanImageOne person, three expressions, one unchanging face — the casting-sheet set used to anchor a character or a real person's likeness.

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.

The layer above prompts

Prompts are single instructions. Skills are procedures your AI keeps — see the Skills Library for SKILL.md files and the setup guide for this platform.

AD PLACEMENT — FOOTER BANNER

Mpromp2 — the AI Prompt Generator. All prompts are free to use, including commercially. Full library: all prompts, all models.