How to Use FASHN Virtual Try-On v1.5 in Gemini CLI
FASHN Virtual Try-On v1.5 creates clothing previews from person and garment photos at 576 × 864 pixels. It handles oversized shirts, baggy jeans, and voluminous dresses while improving preservation of skin texture and tattoos.
Prompts to try with FASHN Virtual Try-On v1.5 in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use FASHN Virtual Try-On v1.5 with the person photo and flat-lay shirts in this project's assets. Create a review gallery with each garment reference beside its generated preview.
Use FASHN Virtual Try-On v1.5 to preview the project's baggy jeans on the selected person photo. Set the garment category to bottoms and save the result beside the reference for silhouette review.
Use FASHN Virtual Try-On v1.5 on the oversized T-shirt photos in the product manifest. Choose a person photo wearing less bulky clothing, and build a contact sheet of the results.
Use FASHN Virtual Try-On v1.5 to compare the project's dress color photos on one person. Treat each dress as a one-piece garment and label each preview with its product color.
Use FASHN Virtual Try-On v1.5 to rerun the example with leftover clothing at the hem using segmentation_free set to false. Show the original result and retry side by side for review.
How to set up FASHN Virtual Try-On v1.5 in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run FASHN Virtual Try-On v1.5
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/fashn/tryon/v1.5", "input": { "model_image": "https://utfs.io/f/wXFHUNfTHmLj4prvqbRMQ6JXFyUr3IT0avK2HSOmZWiAsxg9", "garment_image": "https://utfs.io/f/wXFHUNfTHmLjtkhepmqOUnkr8XxZbNIFmRWldShDLu320TeC" } }'
Then paste one of the prompts above: Gemini CLI finds FASHN Virtual Try-On v1.5 on Spiral, shows the price and runs it.
FASHN Virtual Try-On v1.5 providers and prices
Spiral runs FASHN Virtual Try-On v1.5 through fal. Open a card for today's price, with every fee included.
$0.0975 per generation. Billed on num_samples, default 1.
Settings you can ask for
Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Category | tops, bottoms, one-pieces, or auto | auto | Category of the garment to try-on. 'auto' will attempt to automatically detect the category of the garment. |
| Mode | performance, balanced, or quality | balanced | Specifies the mode of operation. 'performance' mode is faster but may sacrifice quality, 'balanced' mode is a balance between speed and quality, and 'quality' mode is slower but produces higher quality results. |
| Garment photo type | auto, model, or flat-lay | auto | Specifies the type of garment photo to optimize internal parameters for better performance. 'model' is for photos of garments on a model, 'flat-lay' is for flat-lay or ghost mannequin images, and 'auto' attempts to automatically detect the photo type. |
| Moderation level | none, permissive, or conservative | permissive | Content moderation level for garment images. 'permissive' blocks only explicit content; 'conservative' also blocks underwear and swimwear. 'none' disables moderation only for accounts authorized to disable safety filters; for all other accounts it is treated as 'permissive'. |
| Seed | a whole number | Sets random operations to a fixed state. Use the same seed to reproduce results with the same inputs, or different seed to force different results. | |
| Number of samples | 1 to 4 | 1 | Number of images to generate in a single run. Image generation has a random element in it, so trying multiple images at once increases the chances of getting a good result. |
| Segmentation free | on or off | on | Disables human parsing on the model image. |
| Output format | png or jpeg | png | Output format of the generated images. 'png' is highest quality, while 'jpeg' is faster |
Every API field of FASHN Virtual Try-On V1.5 · Image to Image is on its tool page: open its card above.
What can you do with FASHN Virtual Try-On v1.5 in Gemini CLI?
Create clothing previews from the product and person photos in your project. Your coding agent can organize the results into a review gallery with references beside each generated image.
Product page clothing previews
Turn flat-lay garment photos into previews on a chosen person. Review garment lettering, patterns, and edges before selecting images.
Personal shopping comparisons
Apply several photographed garments to the same person photo to compare their appearance side by side.
Oversized denim previews
Show baggy jeans on a chosen person and review the generated folds and silhouette against the garment reference.
Loose clothing catalog images
Create previews of oversized T-shirts and loose dresses. Start with a person wearing less voluminous clothing to reduce leftover fabric.
Garment color comparisons
Use separate product photos of each available color to create a comparison on the same person. Check each result against its own reference.
Fashion content drafts
Try photographed clothing on selected person photos to prepare images for a lookbook or social post. Review body shape, tattoos, and leftover clothing before publication.
More on FASHN Virtual Try-On v1.5 and Gemini CLI
Overview
FASHN Virtual Try-On v1.5 in other agents
Questions about FASHN Virtual Try-On v1.5 in Gemini CLI
Can Gemini CLI use FASHN Virtual Try-On v1.5?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run FASHN Virtual Try-On v1.5 like any built-in tool.
How much does FASHN Virtual Try-On v1.5 cost in Gemini CLI?
$0.0975 per generation. Billed on `num_samples`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need a fal account to use FASHN Virtual Try-On v1.5 in Gemini CLI?
No. Spiral runs FASHN Virtual Try-On v1.5 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up FASHN Virtual Try-On v1.5 in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while FASHN Virtual Try-On v1.5 runs?
FASHN Virtual Try-On v1.5 runs in the background. Gemini CLI starts the run, checks on it and gives you the image when it's ready.
What is FASHN v1.5 useful for?
Use it to create clothing previews for product pages, shopping comparisons, and fashion content. It transfers a photographed garment onto a photographed person.
What resolution does FASHN v1.5 produce?
The documented output is 576 × 864 pixels. Check garment lettering and small patterns at that size before choosing an image for publication.
Can FASHN v1.5 handle oversized clothing?
Yes. Baggy jeans and oversized T-shirts are documented strengths, with improved handling of garment folds and volume.
Will FASHN v1.5 preserve body shape and tattoos?
It improves preservation of body shape, skin texture, and tattoos. Body shape can still shift, so compare the result with the original photo.
Why is some original clothing still visible?
Segmentation-free processing can leave fabric behind when replacing longer or bulkier clothing with a shorter or slimmer garment. Try a person photo with less bulky clothing, or retry with segmentation-free processing turned off.
Start using FASHN Virtual Try-On v1.5 in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


