Every prompt below was generated with Qwen Image 3 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.
“Close portrait of a woman with dewy skin and freckles in soft window light, minimal makeup, calm expression. 35mm film still, soft natural light, muted earth tones with one peach accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Amber glass serum bottle on travertine beside a shallow pool of water, label reading exactly "DEW" with a smaller line "Daily Serum". Clean editorial design, muted earth tones with one amber accent, subtle paper texture, sharp legible type, no other words or logos.”
“Bathroom shelf with skincare jars, a sprig of eucalyptus and a folded linen towel, morning light. 35mm film still, soft natural light, muted earth tones with one eucalyptus green accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Macro of three lipstick bullets in rust, rose and plum resting on honed stone. 35mm film still, soft natural light, muted earth tones with one rust accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
“Minimalist skincare box on a paper backdrop with type reading exactly "SOFT RITUAL" and a smaller line "Night Cream". Clean editorial design, muted earth tones with one lavender accent, subtle paper texture, sharp legible type, no other words or logos.”
“Stacked river stones and a folded towel with rising steam in a stone spa room. 35mm film still, soft natural light, muted earth tones with one slate blue accent, shallow depth of field, subtle film grain, candid and unposed, no text, logos, or watermark.”
Describe the subject and composition; put exact display text in quotes — text rendering is the family strength.
Upload a reference and describe the change to route to the editing endpoint.
Choose square, landscape, or portrait; output renders at the 1K tier.
Check text accuracy and adherence, then adjust one constraint at a time.
Iteration is cheap here: Qwen Image 3 costs 0.4 credits / image, so rewriting a prompt and rerunning it is a normal part of the workflow, not a budget decision. See the full Qwen Image 3 pricing breakdown.
It is the third major version of Alibaba’s open Qwen Image model, adding instruction-based editing and stronger prompt adherence to the family’s reliable text rendering.
More tested prompts across all models live in the prompt library, and the full Qwen Image 3 capability rundown is on the model page.