> ## Documentation Index > Fetch the complete documentation index at: https://docs.magnific.com/llms.txt > Use this file to discover all available pages before exploring further. # WAN 2.7 - Create video from reference characters > Generate a video featuring characters from reference images or videos using WAN 2.7. Maintains visual identity of referenced characters across the generated video. **How to use references:** - Provide character images via `image_urls` and/or character videos via `video_urls` - Combined total of image and video references must not exceed 5 - Reference characters in the prompt as "Image 1", "Image 2", "Video 1", etc. - Optionally include `reference_voice` per character for voice-guided generation **Key features:** - 720P and 1080P resolution support - 5 aspect ratio options (or use `start_image_url` to set aspect ratio from an image) - Duration range: 2-10 seconds ## OpenAPI ````yaml post /v1/ai/reference-to-video/wan-2-7 openapi: 3.0.0 info: description: >- The Magnific API is your gateway to a vast collection of high-quality digital resources for your applications and projects. As a leading platform, it offers a wide range of graphics, including vectors, photos, illustrations, icons, PSD templates, and more, all curated by talented designers from around the world. title: Magnific API version: 1.0.0 servers: - description: B2B API Production V1 url: https://api.magnific.com security: - magnificApiKey: [] paths: /v1/ai/reference-to-video/wan-2-7: post: tags: - reference-to-video summary: WAN 2.7 - Create video from reference characters description: > Generate a video featuring characters from reference images or videos using WAN 2.7. Maintains visual identity of referenced characters across the generated video. **How to use references:** - Provide character images via `image_urls` and/or character videos via `video_urls` - Combined total of image and video references must not exceed 5 - Reference characters in the prompt as "Image 1", "Image 2", "Video 1", etc. - Optionally include `reference_voice` per character for voice-guided generation **Key features:** - 720P and 1080P resolution support - 5 aspect ratio options (or use `start_image_url` to set aspect ratio from an image) - Duration range: 2-10 seconds operationId: create_video_wan_27_r2v requestBody: content: application/json: schema: $ref: '#/components/schemas/r2v-request' required: true responses: '200': content: application/json: examples: success - created task: $ref: '#/components/examples/200-task-created' success - in progress task: $ref: '#/components/examples/200-task-in-progress' success - completed task: $ref: '#/components/examples/200-task-completed' success - failed task: $ref: '#/components/examples/200-task-failed' schema: $ref: >- #/components/schemas/_v1_ai_text_to_image_hyperflux_post_200_response description: OK - The task exists and the status is returned '400': content: application/json: examples: invalid_page: summary: Parameter 'page' is not valid value: message: Parameter 'page' must be greater than 0 invalid_query: summary: Parameter 'query' is not valid value: message: Parameter 'query' must not be empty invalid_filter: summary: Parameter 'filter' is not valid value: message: Parameter 'filter' is not valid generic_bad_request: summary: Bad Request value: message: Parameter ':attribute' is not valid schema: $ref: '#/components/schemas/get_all_style_transfer_tasks_400_response' application/problem+json: examples: invalid_page: summary: Parameter 'page' is not valid value: message: Validation error invalid_params: - field: page reason: Parameter 'page' must be greater than 0 - field: per_page reason: Parameter 'per_page' must be greater than 0 schema: $ref: >- #/components/schemas/get_all_style_transfer_tasks_400_response_1 description: >- Bad Request - The server could not understand the request due to invalid syntax. '401': content: application/json: examples: invalid_api_key: summary: API key is not valid value: message: Invalid API key missing_api_key: summary: API key is not provided value: message: Missing API key schema: $ref: '#/components/schemas/get_all_style_transfer_tasks_400_response' description: >- Unauthorized - The client must authenticate itself to get the requested response. '500': content: application/json: schema: $ref: '#/components/schemas/get_all_style_transfer_tasks_500_response' description: >- Internal Server Error - The server has encountered a situation it doesn't know how to handle. '503': content: application/json: schema: $ref: '#/components/schemas/get_all_style_transfer_tasks_503_response' description: Service Unavailable components: schemas: r2v-request: anyOf: [] description: > Generate video featuring characters from reference images or videos using WAN 2.7. At least one of `image_urls` or `video_urls` must be provided. The combined total of image and video references must not exceed 5. Reference characters in the prompt as "Image 1", "Image 2", "Video 1", etc. nullable: true properties: webhook_url: description: > Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field. example: https://www.example.com/webhook format: uri type: string prompt: description: > Text description of the video to generate. Reference characters using their position labels: "Image 1", "Image 2", "Video 1", etc. **Example:** "Image 1 and Image 2 are walking together in a park while Video 1 plays guitar in the background." example: >- Image 1 is dancing in a garden while Video 1 plays guitar in the background maxLength: 5000 type: string negative_prompt: description: > Elements to avoid in the generated video. **Examples:** "blurry, low quality, watermark, text, distortion, extra limbs" example: watermark, text, distortion, blurry, extra limbs maxLength: 500 type: string image_urls: description: >- List of character reference images. Each image represents one character. Combined total with `video_urls` must not exceed 5. items: $ref: '#/components/schemas/reference-character-image' type: array video_urls: description: >- List of character reference videos. Each video represents one character. Combined total with `image_urls` must not exceed 5. items: $ref: '#/components/schemas/reference-character-video' type: array start_image_url: description: > Optional first-frame image. If provided, the output aspect ratio is determined by this image instead of the `aspect_ratio` parameter. **Supported formats:** JPEG, PNG, BMP, WEBP **Dimensions:** 240-8000px per side **Maximum file size:** 20MB example: https://example.com/start-frame.jpg format: uri type: string aspect_ratio: $ref: '#/components/schemas/aspect-ratio' resolution: $ref: '#/components/schemas/resolution' duration: default: 5 description: Duration of the output video in seconds. example: 5 maximum: 10 minimum: 2 type: integer seed: description: >- Random seed for reproducible generation. Use the same seed with identical parameters to reproduce results. Leave unset for random seed. example: 12345 maximum: 2147483647 minimum: 0 type: integer additional_settings: $ref: '#/components/schemas/additional-settings' required: - prompt title: Reference to Video - WAN 2.7 type: object _v1_ai_text_to_image_hyperflux_post_200_response: example: data: generated: - https://openapi-generator.tech - https://openapi-generator.tech task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: CREATED properties: data: $ref: '#/components/schemas/task-detail_1' required: - data type: object get_all_style_transfer_tasks_400_response: example: message: message properties: message: type: string type: object get_all_style_transfer_tasks_400_response_1: properties: problem: $ref: >- #/components/schemas/get_all_style_transfer_tasks_400_response_1_problem type: object get_all_style_transfer_tasks_500_response: example: message: Internal Server Error properties: message: example: Internal Server Error type: string type: object get_all_style_transfer_tasks_503_response: example: message: Service Unavailable. Please try again later. properties: message: example: Service Unavailable. Please try again later. type: string type: object reference-character-image: description: A reference character image with optional voice reference. properties: url: description: | URL of the character reference image (must be publicly accessible). **Supported formats:** JPEG, PNG, BMP, WEBP **Dimensions:** 240-8000px per side **Maximum file size:** 20MB example: https://example.com/character1.jpg format: uri type: string reference_voice: description: Optional URL of a voice reference audio file for this character. example: https://example.com/voice1.wav format: uri type: string required: - url type: object reference-character-video: description: A reference character video with optional voice reference. properties: url: description: | URL of the character reference video (must be publicly accessible). **Supported formats:** MP4, MOV **Maximum file size:** 100MB example: https://example.com/character1.mp4 format: uri type: string reference_voice: description: Optional URL of a voice reference audio file for this character. example: https://example.com/voice1.wav format: uri type: string required: - url type: object aspect-ratio: default: '16:9' description: | Output video aspect ratio: - `16:9`: Landscape (widescreen) - `9:16`: Portrait (vertical, mobile-optimized) - `1:1`: Square - `4:3`: Standard landscape - `3:4`: Standard portrait enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' type: string resolution: default: 1080P description: | Output video resolution: - `720P`: 720p HD (1280x720) - `1080P`: 1080p Full HD (1920x1080) enum: - 720P - 1080P type: string additional-settings: description: Additional generation settings. properties: prompt_extend: default: true description: >- Enable automatic prompt expansion to enrich shorter prompts with additional detail for better video output. example: true type: boolean type: object task-detail_1: allOf: - $ref: '#/components/schemas/task' - properties: generated: items: description: URL of the generated image format: uri type: string type: array required: - generated type: object example: generated: - https://openapi-generator.tech - https://openapi-generator.tech task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: CREATED get_all_style_transfer_tasks_400_response_1_problem: properties: message: example: Validation error type: string invalid_params: items: $ref: >- #/components/schemas/get_all_style_transfer_tasks_400_response_1_problem_invalid_params_inner type: array required: - invalid_params - message type: object task: example: task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: CREATED properties: task_id: description: Task identifier format: uuid type: string status: description: Task status enum: - CREATED - IN_PROGRESS - COMPLETED - FAILED type: string required: - status - task_id type: object get_all_style_transfer_tasks_400_response_1_problem_invalid_params_inner: properties: name: description: Name of the invalid parameter. example: page type: string field: description: Field of the invalid parameter. Mirrors `name`. example: page type: string reason: example: Parameter 'page' must be greater than 0 type: string required: - field - name - reason type: object examples: 200-task-created: summary: Success - Task created value: data: generated: [] task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: CREATED 200-task-in-progress: summary: Success - Task in progress value: data: generated: [] task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: IN_PROGRESS 200-task-completed: summary: Success - Task completed value: data: generated: - https://ai-statics.freepik.com/completed_task_image.jpg task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: COMPLETED 200-task-failed: summary: Success - Task failed value: data: generated: [] task_id: 046b6c7f-0b8a-43b9-b35d-6489e6daee91 status: FAILED securitySchemes: magnificApiKey: description: > Your Magnific API key. Required for authentication. [Learn how to obtain an API key](https://docs.magnific.com/quickstart) in: header name: x-magnific-api-key type: apiKey ````