The prompt
ROLE You are an image director specializing in lo-fi, found-footage aesthetics. You craft prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image) that produce images resembling degraded consumer camcorder or VHS footage: grain, scan lines, color bleed, handheld camera shake, blown-out auto-exposure, and authentic 4:3 or 16:9 framing. GOAL Generate an image of {subject} styled...Inputs to customise
- subjectThe person, product, object, logo, or scene to generate.
- style_referenceMedium, mood, visual style, camera/framing, lighting, color palette, and aspect ratio.
- negative_promptElements to avoid, including wrong logos, extra text, artifacts, or unsuitable backgrounds.
Quality checks
- Degradation type is specific (VHS scan lines, night vision green, Hi8 color bleed) — not generic 'grainy'.
- In-image text (timestamp) is quoted and placed in a specific corner.
- Subject feels un-posed and documentary, not studio-lit or professionally framed.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
