> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # MiniMax-H3 Character Replace > Replace the main person in a guide video with the person from your photo — face, hair, body and outfit. The original scene, camera motion, movement and audio track are kept. By default the output follows the guide video's length, rounded down to whole seconds (a 14.6-second video gives a 14-second result). The guide video must be at least 5 seconds long; videos longer than 15 seconds are rejected unless you pass `duration`, which renders only their first N seconds. The aspect ratio follows the guide video. If you don't pass `swap_details`, the photo is described automatically and that description is used to transfer the outfit. In videos with several people, use `swap_target` to say which one to replace. **Tips** — a clear, front-facing half-body or full-body photo of a single person works best. Everything else in the frame is kept as-is, including any logos, watermarks or text in the original video. **Pricing** — per second of generated video, in tokens (USD at $0.02/token): | resolution | tokens/s | USD/s | per 5s | |---|---|---|---| | 720p | 2 | $0.04 | $0.20 | Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. ## OpenAPI ````yaml api-reference/video-generations/openapi-minimax-h3-swap.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - MiniMax H3 Character Replace description: Replace the main person in a video with the person from a photo. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/videos/generations: post: tags: - VideoGenerations summary: MiniMax H3 Character Replace description: >- Replace the main person in a guide video with the person from your photo — face, hair, body and outfit. The original scene, camera motion, movement and audio track are kept. By default the output follows the guide video's length, rounded down to whole seconds (a 14.6-second video gives a 14-second result). The guide video must be at least 5 seconds long; videos longer than 15 seconds are rejected unless you pass `duration`, which renders only their first N seconds. The aspect ratio follows the guide video. If you don't pass `swap_details`, the photo is described automatically and that description is used to transfer the outfit. In videos with several people, use `swap_target` to say which one to replace. **Tips** — a clear, front-facing half-body or full-body photo of a single person works best. Everything else in the frame is kept as-is, including any logos, watermarks or text in the original video. **Pricing** — per second of generated video, in tokens (USD at $0.02/token): | resolution | tokens/s | USD/s | per 5s | |---|---|---|---| | 720p | 2 | $0.04 | $0.20 | Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - minimax-h3-swap description: Model name. Must be `minimax-h3-swap`. image_url: type: string format: uri description: >- Publicly accessible URL of the person photo (max 10 MB). This person replaces the main person in the video. A clear, front-facing half-body or full-body photo of a single person works best. video_url: type: string format: uri description: >- Publicly accessible URL of the guide video (max 100 MB, at least 5 seconds). Its main person is replaced; the scene, camera motion, movement and audio are kept. Videos longer than 15 seconds are rejected unless you pass `duration`. duration: type: integer minimum: 5 maximum: 15 description: >- Optional. Render only the first N seconds of the guide video (5–15). Omit it to follow the video's length, rounded down to whole seconds. Must not exceed the actual video length — a longer value is rejected rather than silently clamped. Billing follows the output length. resolution: type: string enum: - 480p - 720p default: 720p description: >- Optional. Accepted values are `480p` and `720p`; the video is always generated at 720p, at the same price. The aspect ratio follows the guide video. swap_target: type: string maxLength: 600 description: >- Optional. In videos with several people, which person to replace. Describe them by position or action (for example "the man on the left" or "the player kicking the ball"), not by clothing. Longer text is truncated to 600 characters. swap_details: type: string maxLength: 800 description: >- Optional. An appearance description of the person in the photo, head to toe (for example "East Asian woman, long black hair, white T-shirt, blue jeans, white sneakers"). If omitted, the photo is described automatically. Longer text is truncated to 800 characters. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - image_url - video_url example: model: minimax-h3-swap image_url: >- https://cdn.goenhance.ai/user/goenhance/76115ad445ce26fbd5ad2c649a29e806.jpg video_url: >- https://cdn.goenhance.ai/user/upload-data/video-to-video/333768e610e442d02e8030693def0b6e.mp4 swap_target: the person in the center of the frame responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 28 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 28 '2': summary: Invalid duration value: code: -1 msg: duration (15s) exceeds the video length (12.0s). '3': summary: Insufficient tokens value: code: 100 msg: tokens is not enough long: summary: Video longer than 15s without duration value: code: -1 msg: >- Video is 20s. Pass duration (max 15s) to use its first part. quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false security: [] ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.