MiniMax Hailuo 2.3
High fidelity AI video generation from text or images
MiniMax Hailuo 2.3
High fidelity AI video generation from text or images
MiniMax Hailuo 2.3 Overview
MiniMax Hailuo 2.3 is a cinematic video model for short form production. It accepts text prompts or image inputs and outputs 6 or 10 second clips at 768p or 1080p. It focuses on consistent motion, strong physics, and stable scenes for ads, social content, and creative shots.
Commercial use
How to Use MiniMax Hailuo 2.3
Overview
Hailuo 2.3 is an AI video generation model that turns text prompts and images into video clips. It focuses on keeping motion stable over time and making sure your characters and visual style don’t drift between frames.
Compared to earlier Hailuo models, version 2.3 behaves more predictably during motion and does a better job of keeping characters consistent. It’s built for day-to-day video generation rather than simple experimentation.
How it Works
Prompt Interpretation
Text prompts guide what appears in the video, how the scene looks, and how things move. Prompts that clearly describe actions or the scene tend to create more reliable clips. You can specify the visual style directly in the prompt, too.
Image-Based Video Generation
For I2V, your generated video will keep the structure and appearance of your input image while adding motion over time. You can use this to animate existing assets or renders without rebuilding the scene.
Motion and Continuity
Hailuo 2.3 produces more stable motion across frames compared to earlier versions. Generated clips show less flicker and do a better job of keeping subjects consistent as the video plays.
Stylization and Visual Content
The model supports both realistic and stylised output. When you define a style the prompt or input image, it generally holds up across the clip without drifting.
Key Features
-
Motion and Continuity Improvements
Produces smoother motion and more consistent results across frames compared to earlier models. -
Character Consistency
Maintains character appearance more reliably throughout a clip. -
Stylisation Support
Handles both realistic and stylized visuals with stable output. -
Text and Logo Handling
Improved stability when rendering text and logos within generated videos.
Technical Specifications
- Model Name: MiniMax Hailuo 2.3
- Model Type: Text-to-video and image-to-video
- Input: Text prompt with optional input image
- Resolution: 768p or 1080p.
- Duration: 6 or 10 seconds (1366×768, default: 6), 6 seconds (1920×1080).
How to Use
- Use a text prompt and/or upload a static image.
- Pick your options, such as duration or resolution.
- Run the generation and see your creation.
- Adjust the prompt or input if you need to refine it.
Example prompt:
“A medium shot of a person walking through a quiet city street at night. The camera slowly tracks forward as the subject walks. Soft street lighting reflects on wet pavement. The scene has a cinematic, realistic style with natural motion.”
Documentation
You can find full usage details, parameters, and examples here:
https://runware.ai/docs/providers/minimax#hailuo-23
More models from MiniMax
MiniMax Music 2.6 is MiniMax’s latest music generation model for full vocal songs and instrumentals from text prompts. It supports natural-language prompts or detailed production-style instructions, follows specified BPM and key with high reliability, and exposes fine-grained song structure control through section tags. The same Music API also supports instrumental generation, lyrics-assisted workflows, and synchronous or streaming delivery.
MiniMax Music Cover is MiniMax’s song-to-song transformation model for reimagining an existing track in a new style. It preserves the original vocal melody while changing voice timbre, instrumentation, genre, and arrangement through a text prompt. It supports one-step generation from reference audio or a two-step workflow with preprocessing and optional lyric editing.
MiniMax M2.7 is a long‑context LLM designed for agentic workflows across software engineering, search and tool use, and high‑value office productivity tasks. It’s built for multi‑step execution, with strong instruction following and dependable task decomposition, making it a solid default for production assistants that write code, call tools, and handle complex document workflows.
MiniMax M2.7‑Highspeed is the performance‑tuned variant of M2.7, built for lower latency and higher throughput while keeping output behavior consistent with the standard model. It’s a strong fit for interactive coding agents, tool‑calling pipelines, and office automation flows where responsiveness matters.
MiniMax-M2.5 is MiniMax’s latest frontier model, optimized for fast, low-cost agentic workflows across coding, search/tool use, and high-value office tasks. Trained with large-scale reinforcement learning in complex real-world environments, it delivers strong reasoning, efficient task decomposition, and high-quality outputs for production assistants and enterprise workflows.
MiniMax Speech 2.8 is an advanced text-to-speech model that turns text into natural, expressive audio in multiple languages. It delivers broadcast-ready speech with rich prosody, emotional control, and a diverse voice library. The model supports up to large input lengths and can be used for voiceovers, narration, accessibility tools, and interactive voice applications.
MiniMax Hailuo 2.3 Fast is the speed tier of the Hailuo 2.3 video family. It targets rapid iteration for social clips, ads, and previews. It produces 6 second 768p or 1080p outputs with smooth motion and stable composition. Ideal for high volume image driven video workflows.
MiniMax Hailuo 02 is a 1080p AI video model for cinematic, high motion scenes. It converts text prompts or still images into short, polished clips with strong instruction following and realistic physics. Ideal for commercial spots, trailers, music promos, and social shorts.
MiniMax 01 Live generates short stylized videos from static anime art. It focuses on expressive character motion with consistent details. Use it to turn illustrations or manga panels into dynamic clips suitable for cutscenes, social posts, or prototype shots.
MiniMax 01 Director generates short cinematic video clips from text prompts with director level control. It supports detailed camera movement instructions, stable framing, and reduced motion randomness. Ideal for film previz, ads, and story beats inside production tools.
MiniMax 01 is a compact text to video model for short clips. It turns simple prompts into 720p videos with smooth motion and cinematic framing. It targets fast iteration and stable output so developers can prototype interactive video features and creative tools with low latency.