Logo
Get Started
Profile

modelrunner / clothes-on-model

Generate realistic on-model fashion photos from your garment/accessory references and an optional model photo.

Official
0.039

Model Input

Input

Scene/background environment.

Optional model/person reference image. Supports public URLs or data URIs.

Optional hat reference image. Supports public URLs or data URIs.

Optional shoe reference image. Supports public URLs or data URIs.

Optional top (shirt, blouse, etc.) reference image. Supports public URLs or data URIs.

Optional bottom (pants, skirt, etc.) reference image. Supports public URLs or data URIs.

Optional dress reference image. Supports public URLs or data URIs.

Min: 1 - Max: 4

The number of images to generate.

Optional additional prompt to refine the clothes-on-model result.

Image aspect ratio.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

preview
preview
preview
Generated in 26.653 seconds
Logs (1 lines)

Model Example Requests

Examples

moU3P3vnVvNaPHOU6XqbC0uLYvm7Bw15Te67eAY4dg

Model Details

Model Details

Clothes-on-Model composes believable, on-model product photos for fashion catalogs and listings. Supply reference images for garments and accessories (and optionally a model photo). The system renders accurate fit, drape, and scale while preserving product design and color.

## Inputs (all optional)

* `prompt` — style/art-direction notes (lighting, crop, mood). * `model_image` — person to wear the items; if omitted, a model is generated. * `dress_image` — a single dress. * `top_image` — a top/outerwear piece. * `bottom_image` — pants/skirt/shorts. * `hat_image` — headwear. * `shoe_image` — footwear. * `aspect_ratio` — e.g., `1:1`, `3:4`, `4:5`, `9:16`, `16:9`. * `num_outputs` — number of images (1–4).

> The render includes only the items you provide. If you include multiple garments that would overlap (e.g., a dress plus top/bottom), results will attempt a sensible composition; for product-accurate listings, include only the pieces you intend to show.

## Output characteristics

* **Use case:** e-commerce and look-book imagery with neutral backgrounds and clean composition. * **Fidelity:** aims to match geometry, color, trims, and construction from your references. * **Fit & drape:** targets realistic cloth behavior and body contact; avoids “floating” items. * **Controls:** `aspect_ratio` and `num_outputs` for layout and batch size.

## How to get the best results

* **Source images:** high-resolution, clear front or ¾ views; minimal occlusion; neutral backgrounds. * **Consistency:** when combining items, prefer similar angles/lighting across all references. * **Clarity:** avoid conflicting products (e.g., two different tops). Provide only what you want shown. * **Prompting:** use the prompt for mood/lighting/crop; let product photos define design and color. * **Framing:** specify commercial crops (e.g., *“half-body, neutral studio backdrop, softbox lighting, subtle depth of field”*).

## Example directions (prompts)

* **Dress focus:** *“Studio catalog shot, knee-up crop, neutral gray paper backdrop, soft directional lighting, natural skin texture, slight depth of field, color-accurate reproduction.”* * **Separate pieces (top + bottom + shoes):** *“Look-book pose, half-body crop, clean white sweep background, soft rim light, true-to-fabric texture, no dramatic gels, product-first composition.”* * **Accessories (hat/shoes only):** *“Three-quarter portrait, neutral studio, gentle vignette, shallow DOF, ensure accessories read clearly, no heavy retouching.”*

## Notes & limitations

* Highly reflective materials, complex prints, heavy embellishments, extreme poses, or strong occlusions can reduce fidelity. * Use rights-cleared imagery. * Avoid prompts that contradict your product photos; reference images take precedence for accuracy.