{"slug": "show-hn-an-ai-video-prompt-cookbook-for-image-to-video-workflows", "title": "Show HN: An AI video prompt cookbook for image-to-video workflows", "summary": "A developer released an AI video prompt cookbook for creators and marketers, providing practical patterns for image-to-video and text-to-video workflows. The cookbook focuses on source image preparation, motion wording, preservation constraints, repeatable testing, and failure review to help users produce usable AI video clips.", "body_md": "Practical prompt patterns for creators testing image-to-video and text-to-video workflows.\n\nThis cookbook is for creators, marketers, and small content teams who need usable AI video clips, not one-off demo prompts. It focuses on source image prep, motion wording, preservation constraints, repeatable testing, and failure review.\n\n- Product marketers turning one product image into a short ad clip.\n- Social creators testing hooks, UGC-style motion, and vertical framing.\n- Brand teams that need a repeatable way to compare AI video outputs.\n- Editors who need clips that can still be cropped, captioned, and reused.\n\nThis is not an API integration guide. The goal is to make prompt testing easier for people who judge the output visually.\n\nUse one prompt card per test so the idea, constraints, and result stay connected.\n\n```\nClip job:\nSource image:\nSubject to preserve:\nMotion:\nCamera:\nFraming:\nStyle:\nNegative constraints:\nSuccess criteria:\nResult notes:\nNext change:\n```\n\nThe two most important fields are `Subject to preserve`\n\nand `Motion`\n\n. Many weak AI video prompts describe the image again, but they do not explain what should move.\n\nUse this when the source image is already the creative anchor.\n\n```\nClip job: 5-second vertical product ad.\nSource image: one clear studio image of the product.\nSubject to preserve: keep the product shape, cap, label, color, and position unchanged.\nMotion: soft light sweeps across the product surface while small background shadows move naturally.\nCamera: slow push-in with stable framing.\nFraming: 9:16 vertical, leave clean space near the top for a caption.\nStyle: realistic ecommerce product video, polished but not over-stylized.\nNegative constraints: no extra objects, no label distortion, no melted edges, no background replacement.\nSuccess criteria: product stays recognizable and the clip can be used in a short ad edit.\n```\n\nUse this when the output needs to feel like a creator shot, but the product still needs to stay readable.\n\n```\nClip job: creator-style social hook for a product recommendation.\nSource image: product held near a simple tabletop background.\nSubject to preserve: keep the product label, package shape, and hand position stable.\nMotion: subtle handheld movement, product tilts slightly toward camera, natural light shifts.\nCamera: close vertical phone shot, mild handheld energy, no dramatic zoom.\nFraming: 9:16, product centered, room for captions on the lower third.\nStyle: clean UGC product clip, realistic, casual, not cinematic.\nNegative constraints: no fake text overlays, no changed packaging, no extra hands, no warped fingers.\nSuccess criteria: the product is readable in the first second and can support a voiceover.\n```\n\nWhen comparing models, keep the job and prompt stable. Do not change the prompt after seeing the first result, or the comparison becomes a prompt rewrite test instead of a model comparison.\n\n```\nTest name: Product bottle, slow push-in, vertical ad.\nInput: same source image for every model.\nPrompt version: v1, unchanged for the first round.\nModels tested: Model A, Model B, Model C.\nScoring: subject fidelity, motion coherence, prompt adherence, editability, retry cost.\nDecision: keep, retry with constraints, or reject for this job.\n```\n\n| Criterion | Weight | What to Check |\n|---|---|---|\n| Subject fidelity | 30% | Product, character, or object stays recognizable |\n| Motion usefulness | 20% | Motion starts early and supports the clip job |\n| Prompt adherence | 20% | Camera, framing, and constraints are followed |\n| Editability | 20% | Clip can be captioned, cropped, or placed in a sequence |\n| Retry cost | 10% | Number of regenerations needed for a usable result |\n\nDo not keep a clip just because it looks impressive. Keep it only if it solves the original clip job.\n\n| Failure | What It Looks Like | Next Prompt Change |\n|---|---|---|\n| Product drift | Shape, color, or label changes | Add stricter preservation constraints and simplify the source image |\n| Background takeover | Background moves more than the subject | Ask for subtle environmental motion and no background replacement |\n| Text distortion | Labels or UI text becomes unreadable | Avoid generating new text; add text later in editing |\n| Motion too static | First seconds barely move | Describe motion that starts immediately |\n| Over-cinematic output | Clip looks like a trailer, not a usable ad | Lower style intensity and specify platform/use case |\n\n```\nai-video-prompt-cookbook/\n  product-video-prompts/\n  ugc-ad-prompts/\n  same-prompt-tests/\n  failure-notes/\n  scorecards/\n```\n\n- Image-to-video workflow:\n[https://lumiying.com/tools/image-to-video](https://lumiying.com/tools/image-to-video)\n\nMIT for prompt templates and scorecard structures. Adapt them to your own product, brand, safety rules, and editing workflow.", "url": "https://wpnews.pro/news/show-hn-an-ai-video-prompt-cookbook-for-image-to-video-workflows", "canonical_source": "https://github.com/yasuomang/ai-video-prompt-cookbook", "published_at": "2026-06-21 11:53:44+00:00", "updated_at": "2026-06-21 12:07:03.902673+00:00", "lang": "en", "topics": ["generative-ai", "ai-tools", "ai-products"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-an-ai-video-prompt-cookbook-for-image-to-video-workflows", "markdown": "https://wpnews.pro/news/show-hn-an-ai-video-prompt-cookbook-for-image-to-video-workflows.md", "text": "https://wpnews.pro/news/show-hn-an-ai-video-prompt-cookbook-for-image-to-video-workflows.txt", "jsonld": "https://wpnews.pro/news/show-hn-an-ai-video-prompt-cookbook-for-image-to-video-workflows.jsonld"}}