fal-tryon
fal-tryon
Virtual try-on — transfer garments onto person photos using fal.ai models.
Scripts
| Script | Purpose |
|---|---|
tryon.sh |
Apply a garment onto a person photo |
Usage
Basic Try-On
./scripts/tryon.sh --person-url "https://example.com/person.jpg" --garment-url "https://example.com/dress.jpg"
With Garment Type
./scripts/tryon.sh --person-url "https://example.com/person.jpg" --garment-url "https://example.com/jacket.jpg" --type top
Arguments
| Argument | Description | Required |
|---|---|---|
--person-url |
URL of person/model photo | Yes |
--garment-url |
URL of garment/clothing image | Yes |
--type |
Garment type: top, bottom, full-body, dress | No (auto-detect) |
--model / -m |
Model endpoint | No (default: fal-ai/fashn/tryon/v1.5) |
--quality |
speed, balanced, quality | No (default: balanced) |
Finding Models
To discover the best and latest virtual try-on models, use the search API:
# Search for try-on models
bash /mnt/skills/user/fal-generate/scripts/search-models.sh --query "try-on"
bash /mnt/skills/user/fal-generate/scripts/search-models.sh --query "virtual tryon"
bash /mnt/skills/user/fal-generate/scripts/search-models.sh --query "garment"
Or use the search_models MCP tool with keywords like "try-on", "tryon", "garment", "fashion".
Tips
- Person photo should show clear full or upper body
- Garment image works best on plain/white background (flat-lay or mannequin)
- Remove garment background first for best results
- Specify garment type (top/bottom/dress) for more accurate placement
More from fal-ai-community/skills
fal-image-edit
Edit images using AI on fal.ai. Style transfer, object removal, background changes, and more. Use when the user requests "Edit image", "Remove object", "Change background", "Apply style", or similar image editing tasks.
859fal-generate
Generate images and videos using fal.ai AI models with queue support. Use when the user requests "Generate image", "Create video", "Make a picture of...", "Text to image", "Image to video", "Search models", or similar generation tasks.
316fal-audio
Text-to-speech and speech-to-text using fal.ai audio models. Use when the user requests "Convert text to speech", "Transcribe audio", "Generate voice", "Speech to text", "TTS", "STT", or similar audio tasks.
269fal-upscale
Upscale and enhance image resolution using AI. Use when the user requests "Upscale image", "Enhance resolution", "Make image bigger", "Increase quality", or similar upscaling tasks.
243fal-3d
Generate 3D models from text or images. Use when the user requests "Create 3D model", "Text to 3D", "Image to 3D", "3D generation", "Generate mesh", "3D asset".
110fal-train
Train custom AI models (LoRA) on fal.ai — personalize image generation for specific people, styles, objects, or video generation. Use when the user requests "Train model", "Train LoRA", "Fine-tune", "Custom model", "Train on my images", "Portrait training".
83