Actions11
- 💬 对话 / Chat Actions
- 🧠 深度思考 / Thinking Actions
- 🖼️ 图片 / Image Actions
- 🎬 视频 / Video Actions
- 📐 向量 / Embeddings Actions
- ✨ 提示词 / Prompt Actions
- 👗 虚拟试穿 / Virtual Try-On Actions
👗 虚拟试穿 / Virtual Try-On → 生成 / Generate
AI-generatedSummary
Generate a virtual try-on image by placing a garment onto a person, with optional AI prompt enhancement and model selection.
Inputs
- model (required) — Model for virtual try-on. Options: Gemini 2.5 Flash Image, Gemini 3 Pro Preview, or custom model via __custom.
- customModel (required) — Custom model ID. Required when model is set to __custom.
- personImageUrl (required) — Person or model image URL.
- garmentImageUrl (required) — Garment image URL.
- category — Garment category. Defaults to upper body. Options: upper, lower, full.
- enhancePrompt — Whether to enhance the try-on prompt before generation. Defaults to true.
- additionalOptions — Collection of optional settings including outputType (url/binary), enhancementModel, temperature, maxTokens, simplify, systemPromptOverride, and extraBodyFields.
Output shape
Returns an array containing a single result object. By default simplified: { success, operation, model, person_image_url, garment_image_url, category, result_image_url, processing_time_ms }. Full output includes raw_content from the model response. When additionalOptions.outputType is binary and an image URL is returned, the image is downloaded and provided as binary data.
If personImageUrl or garmentImageUrl is empty, the operation throws an error. If the model fails to return a valid image URL, success is false and an error note is included.
Examples
Example 1: Basic virtual try-on with Gemini 2.5 Flash Image.
Set model to gemini-2.5-flash-image, provide personImageUrl and garmentImageUrl, leave other parameters at defaults.