Virtual Clothing Try-On
Dress a photo in new clothing (from a garment photo or a description) with identity, pose, and lighting physics locked down.
[Attach: Image 1 = the person. Image 2 = the garment (product photo or flat lay), if you have one.] WITH A GARMENT PHOTO: Dress the person in Image 1 in the [GARMENT: "navy wool overcoat" / "floral midi dress"] from Image 2. Do not change the person's face, facial features, skin tone, hair, body shape, or pose in any way. This must remain unmistakably the same person, same stance. Fit the garment naturally to their body and pose: accurate draping, realistic wrinkles and folds where the pose bends, correct proportions and length for their frame. Match the garment's lighting to the original photo (shadows falling the same direction, highlights consistent with the scene's light source) so it looks photographed, not pasted. Keep the original background [or: "and replace the background with [SETTING]"]. WITHOUT A GARMENT PHOTO (describe the fabric like a tailor): Change the person's outfit to [PRECISE GARMENT LANGUAGE, fabric, cut, color, details: "a charcoal three-piece suit in textured wool, peak lapels, white spread-collar shirt, burgundy grenadine tie" / "an oversized cream cable-knit sweater over straight-leg raw denim"]. Everything else (face, hair, pose, background, lighting) stays exactly as it is. [E-COMMERCE VARIANT, ADD:] Clean studio look: neutral seamless background, soft even lighting, full outfit visible, commercial fashion photography quality. Iterate one change at a time: "same image, sleeves rolled up" / "same outfit in olive green".
How to use
Try-on is one of the most-used image edits (Google built it directly into Shopping) and the two failure points are identity drift and pasted-on lighting, which the lock sentence and the light-matching line exist to prevent. Fabric vocabulary is the quality lever in the no-photo variant: 'textured wool, peak lapels' produces tailoring; 'nice suit' produces costume. For sizing decisions treat results as styling preview, not fit truth: drape is plausible, not measured.
More image prompts
[Attach the reference image, then use this prompt:] Analyze this image and write me a prompt that would reproduce its look with a different subject. First, describe what you actually see, in these terms: - **Subject and composition**: what is in frame, where it sits, how much of the frame it fills, the crop and aspect ratio, the eye lev
Reverse Engineer an Image Prompt
Turn any reference image into a reusable prompt by naming its subject, lighting, lens, palette, and the one detail that carries the look.
Build me a reusable image style kit for [BRAND]. Brand personality in three words: [e.g. "warm, precise, unfussy"] Who it speaks to: [AUDIENCE] Brand colors: [HEX VALUES, or "you propose"] References I like: [DESCRIBE THEM, OR ATTACH THEM] What we must never look like: [THE COMPETITOR OR AESTHETIC TO AVOID] Where these images go: [WEBSIT
Brand Image Style Kit
Define one reusable visual formula so every image you generate looks like it came from the same brand, across subjects and use cases.
Create a t-shirt design. Concept: [THE IDEA, JOKE, PHRASE, OR IMAGE] Exact text, if any: [TYPE IT EXACTLY, WITH THE CAPITALIZATION YOU WANT] Audience and where they would wear it: [WHO BUYS THIS] Style: [bold vintage / minimal line art / retro 70s sunset / hand-drawn / heavy blackwork / kawaii] Shirt color it prints on: [DARK / LIGHT / B
Print on Demand Apparel
Generate t-shirt and merch artwork built for printing: flat color, clean edges, transparent background, and a mockup that sells it.