Search the full model catalog.

Redraws a photo as a cartoon with black outlines and flat color, leaving the person and the background where they were. You only supply the image; there is no text prompt.

Old-master portrait filter: upload a photo and choose one of 12 named looks, from Leonardo da Vinci and Caravaggio styles to Venetian and Northern Renaissance.

Removes every piece of lettering from an image, signs included, and fills the gap with matching background. There is no prompt or mask to supply.

Restyles a portrait photo with an art style and a character persona chosen from two lists, with switches to keep the original outfit and background.

MiniMax's Hailuo S2V-01 makes a video of a person from one face photo and a prompt, keeping their facial features consistent while the prompt sets the scene.

Two-image editing with FLUX.1 Kontext [max]. Put the scene first and the logo or product you want to add second, then describe in plain words where it goes.

MiniMax's T2V-01-Director reads camera moves written in square brackets, like [Push in] or [Pan left], and follows them in a 720p clip of about 6 seconds.

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts.

Edits an image from a plain-language instruction such as "Remove the car", with no mask, and keeps the rest of the picture in place. With no image attached it generates from text.

Text-to-video from MiniMax's 01 series (model T2V-01). A prompt is the only input, and every run returns a landscape 720p clip of about 6 seconds.

MiniMax's I2V-01-Director animates a still image into a 6-second 720P clip and follows camera moves written in square brackets, such as [Pan left] or [Zoom in].

Turns one picture into a 6-second 720P clip with MiniMax's Hailuo I2V-01-Live, the I2V-01 variant made for animating 2D illustrations with steady, subtle motion.

Generate 6s videos with an image. (Also known as Hailuo) MiniMax/image-to-video-01 is the base version of MiniMax’s image-to-video generation model. It takes a single input image and creates a short video clip by simulating motion and dynamic scene transitions. This foundational version provides a balance between visual quality, motion coherence, and runtime efficiency.

Turns a topic prompt into a narrated vertical short with captions synced to the voice and an opening hook title. Six video models are available to render the scenes.

Clone any voice and cover any YouTube song with it. This tool lets you apply a custom-trained RVC voice model to recreate any YouTube song in that voice.

Scores a video with newly generated music. The app picks a musical direction from eight frames of the clip, or takes your prompt, and mixes the track into the clip's audio.

Turns a photo into a song up to four minutes long: a vision-language model reads the image, and ACE-Step v1 3.5B generates the track from that reading plus your genre, mood, instrument and vocal choices.

Turns your lyrics, written with [verse] and [chorus] markers, into a sung track shaped by genre, instrument, mood and voice tags, using the open ACE-Step v1 3.5B music model.

Kokoro is an 82-million-parameter open-weight text-to-speech model. This page reads your text aloud in one of 54 preset voices and returns the speech as an MP3.

Chat with one branch of a GitHub repository: its files are indexed, and the closest matches go to the chat model you select. Private repositories need an access token.