Every prompt below was generated with Grok Imagine Image 2.0 in Made, and the output next to it is what came back — not a curated stock image. Copy a prompt as a starting point, then use the guide underneath to adapt it.
Original results
These examples use media produced for Made. Prompts are included when the production record allows them.
“Festival crowd at dusk with confetti suspended in the air and stage lights washing over raised hands. 35mm film still, soft natural light, muted earth tones with one magenta accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Vinyl records and a turntable on a teak sideboard lit by a warm lamp, sleeves fanned out. 35mm film still, soft natural light, muted earth tones with one orange accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Guitarist tuning a guitar backstage among road cases and cables, tungsten light. 35mm film still, soft natural light, muted earth tones with one red accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Screen-printed gig poster with bold overlapping shapes and a headline reading exactly "THE MIDNIGHT ORCHARD" with a smaller line "LIVE". Clean editorial design, muted earth tones with one hot pink accent, subtle paper texture, sharp legible type, no other words or logos.”
“Retro arcade with glowing cabinets and a lone player silhouetted against the screens. 35mm film still, soft natural light, muted earth tones with one electric blue accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Analog mixing console in a dim recording studio, VU meters glowing amber. 35mm film still, soft natural light, muted earth tones with one amber accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
Lead with the subject, then composition, materials, lighting, and style in concrete language.
Choose from thirteen aspect ratios — including device-native tall formats — at 1K or 2K.
Upload one or more images and describe the change to route the request to the editing endpoint.
Inspect text, faces, and fine detail; the low cost per image makes rapid variation cheap.
Iteration is cheap here: Grok Imagine Image 2.0 costs from 4 credits / image, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the full Grok Imagine Image 2.0 pricing breakdown.
It is xAI’s newest Grok Imagine image model, covering text-to-image generation and reference-based editing at 1K or 2K.
More tested prompts across all models live in the prompt library, and the full Grok Imagine Image 2.0 capability rundown is on the model page.