List available Pruna AI models with capabilities and pricing.

Args: category: Filter by category: image, editing, try-on, upscale, video, video-edit

Generate an image from a text prompt using Pruna AI.

Args: prompt: Text description of the image to generate model: Model to use (default: p-image) aspect_ratio: Output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom) width: Custom width 256-1440, multiple of 16. Only when aspect_ratio=custom height: Custom height 256-1440, multiple of 16. Only when aspect_ratio=custom seed: Random seed for reproducible generation

Edit one or more images with text instructions using Pruna AI.

Args: prompt: Edit instruction describing the desired changes images: 1-5 image URLs or local file paths model: Model to use (default: p-image-edit) aspect_ratio: Output aspect ratio seed: Random seed for reproducible generation

Virtually fit one or more garments onto a person's photo using Pruna AI.

Args: person_image: Image URL or local file path of the person garment_images: 1-11 garment reference images (URLs or local file paths). Up to 6 recommended for best quality. model: Model to use (default: p-image-try-on) prompt: Experimental guidance for non-flatlay garment images (e.g. which garment from which image to use) turbo: Faster generation. Not recommended for more than 4 garments reference_pose: Experimental. Image URL/path to repose the person before try-on seed: Random seed for reproducible generation output_format: Output format (webp, jpg, png) output_quality: Quality for jpg/webp outputs (0-100) preserve_input_size: Resize the result back to the person image size

Upscale an image using Pruna AI.

Args: image: Image URL or local file path to upscale target: Target resolution in megapixels (1-128, capped at 128 MP) output_format: Output format (webp, jpg, png) enhance_details: Enhance fine textures enhance_realism: Improve realism (recommended for AI-generated images)

Upload a local file to Pruna AI for use in editing/video workflows.

Args: file_path: Local file path to upload (max 20MB)

Generate a video from text, image, or audio using Pruna AI.

Args: prompt: Text prompt for video generation model: Model to use (p-video, wan-t2v, wan-i2v, vace) image: Input image URL/path for image-to-video audio: Input audio URL/path for audio-conditioned video duration: Duration in seconds (1-20) resolution: Video resolution (720p or 1080p) aspect_ratio: Aspect ratio (ignored when image is provided) fps: Frames per second (24 or 48) seed: Random seed for reproducible generation

Transform a source video using reference images (video-to-video).

Two models are available:

• p-video-animate: animate a single subject reference image using the motion from the source video (provide exactly 1 reference).

• p-video-replace: replace the character(s) in the source video using 1-3 identity reference images.

Motion, timing, camera movement, and scene structure are preserved.

Args: video: Source video URL or local file path (.mp4) references: Reference images (URLs or local file paths). Exactly 1 for p-video-animate, 1-3 for p-video-replace. model: Model to use (p-video-animate or p-video-replace) resolution: Output resolution (720p or 1080p) target_fps: Working FPS (original, 24, or 48) instruction_prompt: Optional guidance on how to apply the transform turbo: Faster generation for slightly lower quality save_audio: Save the output video with audio ignore_audio: Ignore source audio during generation seed: Random seed for reproducible generation