MuAPIInstall

Summary

Generate AI media including images, videos, and audio by specifying a category and model, then providing parameters appropriate to the selected generative task and model.

Inputs

• category (required) — Select the type of generative task to perform: text to image, image to image, text to video, image to video, image enhance, video edit, or audio.
• model (required) — Choose the specific AI model within the selected category to perform the generation or processing.
• prompt (required) — Provide a textual description guiding the generation; used for text-to-image, text-to-video, or audio creation, depending on category and model.
• width — Specify image width in pixels for models that accept pixel dimension parameters.
• height — Specify image height in pixels for models that accept pixel dimension parameters.
• aspect_ratio — Select the output aspect ratio for the generated image or video when supported by the model.
• num_images — Set the number of images to generate for text-to-image models that support this parameter.
• negative_prompt — Input content to avoid in generated images for models that support negative prompting.
• i2i_prompt (required) — Text instruction to edit images for image-to-image models.
• images_list (required) — Comma-separated URLs of input images for image-to-image tasks on supported models.
• name (required) — Effect name to apply in certain image-to-image models for applying creative effects.
• effects_image_url (required) — URL of image to apply creative effects on for applicable models.
• t2v_prompt (required) — Text description for text-to-video generation tasks.
• t2v_aspect_ratio — Aspect ratio selection for output video for text-to-video models supporting it.
• t2v_resolution — Video resolution setting for certain text-to-video models.
• t2v_duration — Duration in seconds for generated videos, supported by some text-to-video models.
• i2v_prompt (required) — Text description guiding video generation from images for image-to-video models.
• i2v_image_url (required) — Single image URL input for image-to-video models that require one image.
• i2v_images_list (required) — Comma-separated URLs for multiple input images (1-2) for image-to-video models supporting this.
• i2v_aspect_ratio — Aspect ratio for output video in image-to-video generation, if supported.
• i2v_resolution — Resolution setting for image-to-video generation for supported models.
• i2v_duration — Duration in seconds for image-to-video generated video where applicable.
• enhance_image_url (required) — URL of the image to enhance using various image enhancement models.
• faceswap_image_url (required) — Target image URL for face swap in image enhancement category.
• faceswap_swap_url (required) — Source face image URL to use in face swap operations.
• erase_image_url (required) — Image URL to process for object erasing.
• erase_mask_url (required) — Mask image URL indicating the area to erase in the source image.
• product_image_url (required) — Product image URL to generate product photography scene.
• scene_description (required) — Text description describing the scene for product shot generation.
• anime_prompt (required) — Prompt for generating an anime-style image.
• anime_width — Width in pixels for anime image generation.
• anime_height — Height in pixels for anime image generation.
• wan_prompt (required) — Effect description prompt for WAN AI effects video editing.
• wan_image_url (required) — Image URL to apply WAN AI effects in video edit category.
• wan_effect_name (required) — Name of the WAN effect to apply.
• wan_aspect_ratio — Aspect ratio for the WAN effect video output.
• wan_quality — Quality setting (Medium or High) for WAN effects.
• wan_resolution — Resolution (480p or 720p) for WAN effect output.
• wan_duration — Duration in seconds for the WAN effect video.
• vfaceswap_image_url (required) — Source face image URL for video face swap.
• vfaceswap_video_url (required) — Target video URL for video face swap.
• vfaceswap_target_gender — Target gender filter for video face swap (All, Female, Male).
• dress_model_image_url (required) — Person image URL for dress change video editing.
• dress_garment_image_url (required) — Clothing or garment image URL for dress change.
• clip_video_url (required) — Video URL for AI clipping to create highlights.
• clip_num_highlights — Number of highlights to clip from the video.
• clip_aspect_ratio — Aspect ratio for AI clipped video highlights.
• lipsync_video_url (required) — Target video URL for lipsync processing.
• lipsync_audio_url (required) — Audio URL to sync with the target video lips.
• suno_style (required) — Musical style or genre for Suno music creation.
• suno_prompt — Lyrics or prompt text for the song; leave empty for instrumental.
• suno_model — Suno AI model version to use for music generation.
• suno_instrumental — Boolean to generate instrumental music without vocals.
• suno_track_id (required) — Track ID of Suno music to remix or extend.
• suno_remix_style — New style description for remixing a Suno track.
• audio_prompt (required) — Text description for audio generation in MMAudio models.
• audio_duration — Duration in seconds for audio generation (1-30 seconds).
• audio_video_url (required) — Video URL to generate audio for in MMAudio video-to-audio model.
• options.maxWaitSeconds — Maximum number of seconds to wait for the task to complete (default 600).
• options.pollIntervalSeconds — Polling interval in seconds to check task status (default 3).
• options.returnRequestIdOnly — If true, returns the request_id immediately without waiting for task completion (default false).

Output shape

a list of JSON objects representing either the generation result or errors per input item

Returns generation results including status and returned media data once completed, or an error object if failed. If 'returnRequestIdOnly' is true, returns only the request_id and submission info immediately.

Links

• n8n community nodes installation guide