Clothes Try-on Studio

A generation skill: try on clothes, optionally change the background, optionally turn the result into a short motion video.

When to trigger

When the user wants to try clothes on virtually. For makeup, hair, or skin, hand off to the matching skill.

Ask first (this skill has multiple generation steps) and state cost

Before generating, ask the user which steps they want and tell them the credit cost of each:

• Try on clothes (cloth-v4) — required base step
• Change background (bg-replace) — optional
• Motion video (image-to-video) — optional; note video is billed per second Get costs with python scripts/youcam_core.py cost --feature cloth-v4 (and --feature bg-replace, --feature image-to-video), tell the user the total, and only run what they choose.

Get the latest API spec (do this every run)

• Clothes: https://docs.perfectcorp.com/reference/ai_clothes.md (latest engine cloth-v4)
• Background change: https://docs.perfectcorp.com/reference/ai_photo_background_change.md
• Video generator: https://docs.perfectcorp.com/reference/ai_video_generator.md Pass --version if newer than api-fallback.yaml.

Prerequisites

1. A photo of the person (full-body or upper-body) plus one garment reference image (product or worn photo) or a template_id.
2. Run python scripts/youcam_core.py validate-key (0 credits) to confirm the key. If it is not set, tell the user to get one at https://yce.perfectcorp.com/api-console and set the YOUCAM_API_KEY env var, or create credentials.json in the skill root (see credentials.example.json for the format).

Flow (only the chosen steps)

1. Try on (cloth-v4):

   python scripts/youcam_core.py run --feature cloth-v4 --src_file <person.jpg> --ref_file <garment.jpg> \
       --param garment_category=full_body
   

   (or use a template: --param template_id=<id>; confirm the exact garment_category value from the latest doc — see Notes.)
2. (Optional) Change background (bg-replace): on the result or original image, run --feature bg-replace --src_file <img> --param type=prompt --param prompt="A sunny beach" or use a preset background: list them with python scripts/youcam_core.py templates --feature bg-replace (0 credits; each has an id, title, and thumb image; pass --starting_token <next_token> for the next page), let the user pick one, then run --feature bg-replace --src_file <img> --param type=template --param template_id=<id>.
3. (Optional) Motion video (image-to-video): run --feature "image-to-video" --src_file <img> --param resolution=720 --param dst_duration=5 --param prompt="turn around / runway walk"
4. Each generation returns a result image/video URL in data.results.url.
5. If run prints "task_status": "running", the task is still processing and run stopped waiting. Do not run it again, since that starts a new task and charges again. Check back with python scripts/youcam_core.py status --feature <feature> --task_id <task_id>, using the task_id from that output, until task_status is success or error. A task_id stays valid for 24 hours.

Output rules

• Return the result image/video URL exactly as given (hyperlink is OK; do not modify or shorten it).
• Video can take longer than run's default wait. If it returns running, check back with status as in step 5.
• Always end with this note: "This try-on image/video is AI-generated and for reference only; actual fit and appearance may vary."

Notes

cloth-v4 garment_category is confirmed for full_body; the upper/lower-body token spelling is not yet 100% confirmed, so verify it against the latest doc parameter table before running (see the handoff GAPS).