REFERENCE-TO-VIDEO
MiniMax H3 Max Ref-to-Video generates video from your own references. Bring multiple images, video clips, and audio, cite them in your prompt as Image 1, Video 1, and Audio 1 in input order, and the model weaves them into a new 5-to-15-second clip at 480p or 768p. It's the reference-driven member of the MiniMax H3 Max family. Available now in Picsart's AI Playground.
REFERENCE-DRIVEN VARIANT
MiniMax H3 Max Ref-to-Video is the reference-driven member of the MiniMax H3 Max family. Instead of starting from a blank prompt, you feed it multiple reference images, video clips, and audio files, then describe how to use them. It generates a new clip of 5 to 15 seconds at 480p or 768p, in adaptive or fixed aspect ratios from 21:9 to 9:16 - grounding the result in the material you provide.
CITE BY INDEX
Ref-to-Video reads the references you attach in order and lets you point to them directly in the prompt - Image 1, Video 1, Audio 1, and so on. Pull a character from one image, a motion or setting from a video clip, and a voice or soundtrack from an audio file, then describe how they should come together. The model composes a single coherent video that honors each reference, so your source material shapes the shot instead of a text description alone.
What MiniMax H3 Max Ref-to-Video is great for
Provide reference images of a character or product and keep them on-model across a new clip, driven by the references you supply.
ONE COHERENT CLIP
Ref-to-Video is built for control: attach as many images, clips, and audio files as your shot needs, then use the prompt to direct exactly how each is used. Choose 480p or 768p, set a length from 5 to 15 seconds, and pick an adaptive ratio or a fixed one from 21:9 to 9:16. The result stays grounded in your material while the model handles motion and continuity - so your references become a finished video, not a mood board.
NO KEYS, NO SETUP
MiniMax H3 Max Ref-to-Video is available in Picsart's AI Playground, where you upload references, write your prompt, and generate - then compare the result against 150+ other AI models from a single prompt, with no setup required. Want the fastest text- and image-to-video instead? MiniMax H3 Max Turbo; need native 2K with audio? MiniMax H3. And you can reach it whichever way you work: on the web, in the Picsart desktop app, or built into your own projects via CLI, MCP, REST API, and SDK.
MiniMax H3 Max Ref-to-Video is the reference-driven member of the MiniMax H3 Max family. It generates a new video from reference images, video clips, and audio you supply - you cite them in the prompt as Image 1, Video 1, Audio 1 - at 480p or 768p, from 5 to 15 seconds.
Attach multiple images, videos, and audio files; they're read in input order, and you point to them directly in your prompt (Image 1, Video 1, Audio 1). The model composes a single clip that honors each reference alongside your instructions.
MiniMax H3 Max Turbo is the fastest text- and image-to-video variant, tuned for real-time iteration. Ref-to-Video is built to generate from multiple references - images, clips, and audio - when you want the output grounded in source material you provide.
MiniMax H3 renders native 2K with synchronized audio. Ref-to-Video focuses on reference-driven generation at 480p or 768p - choose it when your shot starts from images, clips, and audio you already have.
New 5-to-15-second clips at 480p or 768p, built from your reference images, video clips, and audio - great for keeping a character on-model, compositing from several clips, or matching a specific look and sound.
It's available in Picsart's AI Playground. You can also use it on the web, in the Picsart desktop app, and build it into your own projects via CLI, MCP, REST API, and SDK.
Yes. Videos created through Picsart's tools powered by MiniMax H3 Max Ref-to-Video can be used for marketing, social media, brand content, and other commercial applications, subject to Picsart's terms of use.
Compare MiniMax H3 Max Ref-to-Video with other video models for reference-driven AI video.
Generate AI video with MiniMax H3 Max Ref-to-Video
AI tools for everyday creative work.
Heavy AI usage for creators & teams.
Custom AI solutions for large organizations.
Learn how to compare video models and choose an output.
