pruna – AI APIs, Models, LLMs, Pipelines & Functions

p-image-try-on

Pruna’s p-image-try-on creates virtual try-on images by applying one or more garment photos to a person photo. Generate up to 11 outfit variants in one run.

Image to Image

Run

p-video-replace

pruna

Replace a subject in a source video using 1–3 reference images. Preserves the original motion and can keep the source audio in the final MP4.

Image to Video

Run

wan-i2v

pruna

Pruna's WAN I2V animates one still image into a short MP4 video with prompt-driven motion. Pick 480p or 720p, plus optional last-frame control.

Image to Video

Run

wan-t2v

pruna

Pruna’s WAN T2V generates a short MP4 video from a detailed scene prompt. Pick 480p or 720p, choose 16:9 or 9:16, and control motion and safety options.

Text to Video

Run

p-video-avatar

pruna

Generate a lip-synced talking avatar video from a single portrait image plus a script or uploaded audio. Pick a voice, language, and 720p or 1080p output.

Image to Video

Run

p-video

pruna

Generate videos from text prompts or images using P-Video AI. Supports various resolutions and customization options.

Text to Video

Run

vace

pruna

Vace powered by Pruna AI

Text to Video

Run

qwen-image-edit-plus

pruna

Qwen Image Edit Plus powered by Pruna AI

Image to Image

Run

wan-image-small

pruna

wan-image-small is a highly optimized, resource-efficient AI model that rapidly generates high-quality, cinematic images from text using the Pruna AI framework.

Text to Image

Run