Every prompt below was generated with Z Image 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.
“Swimmer in a lake at dawn, mist on the water, pine silhouettes on the far shore. 35mm film still, soft natural light, muted earth tones with one orange cap accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Runner on a coastal cliff path at sunrise, mid-stride, soft sea mist in the distance. 35mm film still, soft natural light, muted earth tones with one coral accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Climber reaching for a hold on an indoor bouldering wall, chalk dust in the air. 35mm film still, soft natural light, muted earth tones with one yellow accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Rolled natural light-brown cork yoga mat with visible cork grain and a steel water bottle on a pale wooden studio floor, long window shadows. 35mm film still, soft natural light, muted earth tones with one sage accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Cyclist on a gravel road through golden wheat fields, dust trailing behind the wheels. 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.”
“Foam roller, folded towel and a glass of iced matcha on a wooden locker-room bench, soft light. 35mm film still, soft natural light, muted earth tones with one matcha green accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
Start with the subject and action, then add setting, composition, lighting, and finish.
Select a square, portrait, or landscape preset that matches the intended placement.
Use the exposed format, step, guidance, and acceleration controls when you need them.
Wait for the queued job to finish, then inspect fine text and anatomy before download.
Iteration is cheap here: Z Image costs 0.2 credits / image, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the full Z Image pricing breakdown.
Z Image is a text-to-image model routed through fal.ai for fast, flexible concept generation.
More tested prompts across all models live in the prompt library, and the full Z Image capability rundown is on the model page.