Is there a Claude Code skill that puts my clothes on an AI model?

Yes, Wireflow's ai-fashion-model-photos-for-ecommerce skill puts your clothes on an AI model in Claude Code, starting from one flat-lay or ghost-mannequin photo of the garment. It writes a model brief and a lifestyle setting, shows the credit cost and waits for your yes. Then it renders three catalog shots in one call with Nano Banana Lite and saves them to ./wireflow-outputs/.

Claude does the planning, and the rendering runs as a published Wireflow app through the Wireflow MCP connector, signed in as you. Without the connector, the skill still gives you the free part of its model brief pack: a garment photo checklist, a filled-in model brief and three shot prompts that work in any image editor that takes a reference photo. The skill's files, including the model brief pack, are in its folder in the wireflowINC/skills repo.

For a product shown alone in a scene, use the product-photography skill instead. For a listing gallery made from one product photo, see the amazon-product-images skill.

How do I install the fashion model photo skill in Claude Code?

Add the Wireflow plugin, which brings every Wireflow skill plus the Wireflow connector. In Claude Code, run:

/plugin marketplace add wireflowINC/skills
/plugin install wireflow-skills@wireflow

Claude Code shows you the plugin's details first, so you can review it and choose its scope. Next, run /mcp, choose wireflow and sign in with your Wireflow account. You can then call the skill as /wireflow-skills:ai-fashion-model-photos-for-ecommerce, or describe what you want and Claude picks it up.

To install only this skill, add it with the skills CLI, or copy its folder from the repo into ~/.claude/skills/ (all projects) or .claude/skills/ (one project). Then connect Wireflow yourself and run /mcp to sign in. The connector uses OAuth, so there is no API key to copy.

npx skills add wireflowINC/skills --skill ai-fashion-model-photos-for-ecommerce
claude mcp add --transport http wireflow https://www.wireflow.ai/api/mcp

To check that it works, ask in plain words:

Put my navy linen shirt on an AI model for my online store. I have a flat-lay photo of it.

If the Wireflow tools are connected, the skill asks for your photo and starts planning. If they are missing, it says so in one sentence, gives you the setup and still hands you the checklist, brief and prompts from its model brief pack. Claude also uses the skill when you ask for on-model photos, a model shot from a flat lay, apparel catalog images or the same garment on different models.

To run your own Wireflow workflows from code with an API key instead, see the run API reference.

What photo do I need to give Claude?

You need one photo of one whole garment, laid flat or on a ghost mannequin, front side up, in even light with true color. The skill checks it against the garment photo checklist in its model brief pack and tells you what would help, but small issues do not stop it.

The photo must be reachable at an https:// URL:

• Already online: the skill uses the direct image link.
• A file on your computer: the skill gives you an upload link from the Wireflow connector that works on a phone with no login. Once you confirm the upload, it uses the file's URL.
• No upload tools: the skill asks for a public direct link, such as one from your store CDN or a cloud drive.

Each run takes one garment. For a top worn with bottoms you also sell, plan two runs, or describe the bottoms in the model brief, knowing that a described piece is generated, not your product.

Claude also asks you once, in one message, who your buyer is, the look of your store (studio, street, beach or office) and any model your brand already uses, described in words, never a real person's name or photo.

From your answers, it writes the model brief: age range, build, skin tone, hair, expression and the plain items that complete the outfit, such as white sneakers. It also writes the lifestyle setting: place, time of day, light and one or two background details, simple enough that the whole garment stays visible. It shows both in a short table, and you can edit any word. Every run then sends three inputs:

Input	What it holds	Limit
garment_photo	The https:// URL of one garment, flat lay or ghost mannequin	Required on every run
model	Who wears it: age range, look, hair, expression, plus plain shoes or bottoms if the outfit needs them	Up to 2,000 characters
lifestyle_setting	Place, light and mood for the third shot	Up to 2,000 characters

The skill always sends all three, because a missing input falls back to the board's saved demo (a sage green shirt dress, a curly-haired model, a cobblestone street), and you would pay for photos of someone else's dress. For the same garment on several models, such as a size-inclusive range or different looks, it plans one run per model.

Use only garment photos you have the right to use. The skill uses generated models only: it will not put your garment on a real, identifiable person such as a celebrity, influencer or employee, unless that person is you and you asked. Wireflow's Privacy Policy says it does not use your prompts, images or generated content to train AI models.

What do I get back from a run?

You get three 3:4 JPEGs from one call: a full-length front shot and a full-length 3/4 shot, both on a plain light grey seamless backdrop, plus a candid lifestyle shot in your setting.

Output	Shot	Backdrop
front	Full-length, from the front	Plain light grey seamless backdrop
three-quarter	Full-length, 3/4	Plain light grey seamless backdrop
lifestyle	Candid lifestyle pose	The lifestyle setting from your brief

In the skill's test, each image was 896x1200 and the run took about 20 seconds. The skill checks the run every 5 seconds. If it ends as FAILED, CANCELLED or TIMEOUT, the skill stops and quotes the error, and when Wireflow refuses a request or a tool errors, it quotes the exact message.

It saves the images under ./wireflow-outputs/, in a folder for the date and then a fashion folder, with the garment, the model and the shot in each file name. It ends with a table of each file, its shot and its link, plus the credits used.

It then offers the same garment on another model, or the same model in your next garment, with one quote for the batch. It also offers its board in Wireflow, where you can change the backdrop or the ratio, or add a background remover.

Wireflow's Terms of Service say content generated by AI models through Wireflow is yours to use for personal and commercial purposes, subject to the underlying AI model provider's terms. Some marketplaces and countries have rules on AI-generated people in listings and ads, so check the rules that apply to you. The skill does not promise compliance.

Does it change my garment?

It is set up not to: a fixed rule block in the app keeps your garment's cut, length, color, fabric, collar, buttons, pockets, seams, trims and prints as photographed. A shot can still miss a detail, so the skill checks every image against your photo before it calls the job done.

Before the run, it writes your garment's details in one line, for example "sage shirt dress, point collar, seven white buttons, chest pocket, tie belt, tab cuffs". After the run, it compares each shot with your photo and that line:

• Same color, fabric look and print.
• Same collar, buttons (counted when they show), pockets, cuffs, belt and trims.
• Same length and fit. Models often wear a dress shorter or a shirt looser than the flat lay suggests.
• Nothing added: no extra logos, bags, jackets or jewelry the brief did not ask for.
• Hands, feet and faces that look natural.

It flags every miss by file, such as "the lifestyle shot added a brown shoulder bag". A redo is a new run of 48 credits, and it runs only after your yes.

The model brief keeps extras such as shoes and jeans neutral, so the garment stays the focus. The skill does not invent fabric claims, sizes, certifications or prices in any image or caption.

How many credits does one run cost?

One run costs 48 credits for all three shots, which is 16 credits per image, as measured on 15 October 2026 with Nano Banana Lite.

What	Credits
Model brief, setting, photo check and the quote	0
One run: front, 3/4 and lifestyle shots	48 credits per run, 16 per image (Nano Banana Lite, measured 15 Oct 2026)
A redo, or the same garment on another model	48 more per run, only after your yes

Before anything runs, the skill checks your balance and shows a quote such as "1 run x 48 credits = 48 credits for 3 on-model photos", with your balance next to it. For several models or garments, it multiplies and shows the total. If your balance is too low, it stops and tells you.

Nothing runs until you say yes to the plan and the cost. Afterwards, the skill reports the credits used, worked out as your balance before minus after.

Rendering needs a Wireflow account with credits. See pricing for what each plan includes.

Does the fashion model photo skill work in Cursor, Codex or Claude Desktop?

It is written for Claude Code and Claude, and the skills CLI also installs it in Cursor, Codex and other agents that read SKILL.md, but every agent needs the Wireflow MCP connector before the skill can render anything. Wireflow has not tested its skills in those other agents itself.

In Claude.ai and Claude Desktop, add https://www.wireflow.ai/api/mcp as a custom connector. Saving the images needs a shell, and the skill's closing table also lists a link to each shot.

To connect each agent, see the guides for Cursor and Codex, or Use Wireflow from your agent for every client. The agent skills page explains how the Wireflow skills work and lists the others.