Bring every shot
to life with Hailuo
Describe a scene or start from a still, and get a finished clip back.
Try HailuoMeet Hailuo
Text to Video
Write the scene, then pick length, resolution and aspect ratio on MiniMax H3, or use Hailuo 2.3 for physics-aware motion.
Try it nowImage to Video
Start from a first frame and let the motion run. Hailuo 2.3 and MiniMax H3 both animate stills, and H3 also takes an optional last frame.
Try it nowReference to Video
Combine up to 9 images, 3 video clips and 3 audio tracks to keep subjects and timing consistent.
Try it nowVideo Edit
Upload a clip and describe the change, with optional reference images or audio.
Try it nowMade with Hailuo
Open the generatorHailuo 2.3 Standard Text to Video
Camera: An extreme low-angle, shaky cam shot, looking up as a massive alien dreadnought descends onto a barren red planet. The camera is pushed back slightly by intense wind and vibration. Effect: The landing thrusters kick up a colossal plume of red dust and sand, creating a shockwave. The intense plasma exhaust from the engines superheats the ground, causing it to visibly vitrify (turn to glass). Sounds: An extremely deep, chest-thumping bass rumble (LFE), mixed with a high-pitched engine whine and storm-like wind howling. The grating sound of metal on rock. Mood: Epic, awe-inspiring, oppressive, and ominous. Lighting: Harsh, unnatural blue light from the ship's engines contrasts with the dim, dusty red daylight of the planet, creating stark, moving shadows.
Try it nowHailuo 2.3 Pro Text to Video
Camera: First-person perspective (POV), the beam of a flashlight is the only viewpoint. The camera moves tensely and slowly down a pitch-black, decaying hospital corridor. The camera suddenly jerks to the right. Effect: The flashlight beam only illuminates a few feet ahead, catching dust motes in the air. As the camera jerks right, the beam briefly illuminates a pale face that vanishes in less than half a second. Voices/Sounds: Only the character's shaky, shallow breathing and the distant echo of a single water drop. A short, sharp violin screech (stinger) hits the moment the face appears. Mood: Extreme tension, claustrophobic, jump-scare, deep unease. Lighting: Total darkness, punctuated only by the narrow, cold-white beam of the unstable handheld flashlight.
Try it nowHailuo 2.3 Pro Image to Video
The chef tosses the vegetables in the wok as flames flare up, steam rising, the camera slowly pushes in.
Try it nowHailuo 2.3 Fast Image to Video
Motion: The woman naturally raises the perfume bottle from her side toward the camera, tilting it slightly as she rotates her wrist to catch the light. The camera smoothly tracks the product’s motion, performing a gentle forward dolly combined with a slow orbit. When she pauses, the focus subtly shifts to the glowing glass surface. Camera: Perfectly synchronized follow shot with fluid handheld realism. Smooth autofocus transitions and stable depth tracking — no jitter or distortion. The motion arc is wide enough to show dynamic camera behavior but remains physically natural. Lighting: Dynamic reflections move across the bottle as the camera circles. The lighting softly adapts to the new angles, revealing the transparency and shimmer of the glass in realistic detail. Sound: Soft ambient tones, light fabric movement, subtle glass resonance, and a warm, cinematic underscore. Style: Cinematic realism with natural human motion, physically accurate light interaction, and fluid camera following — a clear demonstration of Hailuo 2.3’s precision in temporal coherence and realistic rendering.
Try it nowHailuo 2.3 Fast Pro Image to Video
[0-2s] - Medium shot of her resolute face, focusing on her glowing eyes, slowly panning down to her weapon. [2-4s] - Quick cut to a dynamic low-angle tracking shot as she rapidly scans her surroundings, her gaze sharp and focused, slight head movement. [4-6s] - She suddenly shifts her weight and lunges forward out of frame, a quick, powerful burst of movement, disappearing into the city mist, leaving a lingering sense of urgency and mystery.
Try it nowHailuo 2.3 Standard Text to Video
Camera: A slow, ethereal crane shot begins high above, looking down as a ballerina begins an elegant pirouette on a shimmering, moonlit stage. The camera slowly descends and gently orbits her as she spins. Effect: Her white tutu shimmers with a faint, magical stardust glow that gently drifts upwards. As she extends her arm, a delicate, translucent ripple effect emanates from her fingertips. Sounds: Soft, ambient orchestral music with light, echoing piano notes. A gentle chime sound effect as the stardust appears, and a subtle whoosh with the ripple. Mood: Graceful, enchanting, and otherworldly. Like a dance within a dream. Lighting: Soft, cool moonlight, subtle spotlight on the dancer, with a magical, diffused glow from the stage floor.
Try it nowHailuo 2.3 Pro Text to Video
Camera: A slow, steady wide shot (as if gently floating) that moves through a dense, lush, sun-dappled forest. The camera pauses slightly as it reveals a small, friendly forest spirit. Effect: Tiny, glowing dust motes (tree spirits / Kodama) slowly drift and sparkle through the shafts of sunlight. Leaves on the trees gently sway in a soft, visible breeze. A small, forest spirit (like a Kodama or Totoro-esque creature) blinks slowly and turns its head, then nods gently to the camera. Sounds/Voices: Soft, ambient forest sounds: the gentle chirping of unseen birds, the distant trickle of water, and the rustling of leaves in the breeze. A delicate, whimsical flute melody plays softly, accompanied by a faint, magical "tinkle" when the spirit nods. Mood: Whimsical, peaceful, magical, enchanting, and serene. A sense of wonder and gentle calm. Lighting: Warm, golden, dappled sunlight filters through the dense tree canopy, creating soft, glowing patches on the forest floor and highlighting the lush greenery. Subtle lens flares appear in the brightest areas.
Try it nowHailuo 2.3 Standard Image to Video
A vibrant K-pop girl group of four members, each with unique, colorful hairstyles and stylish stage outfits, performs a high-energy, perfectly synchronized dance routine on a brightly lit concert stage. They execute sharp, precise movements with powerful grace, transitioning seamlessly between formations. Their expressions are confident and charismatic, engaging directly with the audience. Dynamic camera angles capture their full body choreography and close-ups of their captivating visuals. Fast-paced, energetic, pop concert atmosphere, glamorous, bold fashion, professional choreography, bright spotlights, fan cheering implied, blockbuster music video quality.
Try it nowHailuo 2.3 Pro Image to Video
Camera: A smooth, slow 360-degree orbit shot around the floating earbud (Part 1). The camera slowly dollies in, focusing on the brushed metallic texture. As it gets extremely close, the earbud moves forward, filling the frame. We match-cut to an intimate close-up of a person's ear as their hand brings the same earbud into frame and inserts it. The camera then pulls back slightly to show their satisfied profile. Effect: (Part 1) The earbud rotates weightlessly; light streaks orbit it. (Part 2) As the camera pushes through, the background cross-fades from the abstract purple/blue gradient to a soft-focus, stylish apartment. The person smiles gently and closes their eyes as they put the earbud in, signifying immersion. Sounds/Voices: The minimalist electronic track swells during the transition. As the earbud is inserted, a soft, satisfying "chime" (like a 'connected' sound) plays, perfectly synced with a subtle bass drop. The music then continues, now feeling warmer and more ambient. Mood: Begins as "Premium, futuristic, sophisticated," then transitions to "Personal, immersive, comfortable, and satisfying." Lighting: (Part 1) Polished, cool studio lighting. (Part 2) Transitions to warm, soft, indoor lifestyle lighting (e.g., soft morning light from a window) that casts a gentle glow on the person's face. The earbud itself still catches a perfect, clean highlight.
Try it nowPick your Hailuo
MiniMax H3
The full toolkit: text, image and reference to video plus video editing, 480p to 1080p, clips from 3 to 15 seconds.
Try it nowHailuo 2.3
Physics-aware text and image to video: Standard at 768p and Pro at 1080p, with 6 or 10 second clips on Standard.
Try it nowHailuo 2.3 Fast
Hailuo 2.3 Fast and Fast Pro for quick image to video: 6 or 10 seconds at 768p, or 6 seconds at 1080p.
Try it nowModels and pricing
Prices are per generation and update live. Options such as resolution, duration or quality can change the final price, which the generator shows before you run.
| Model | Input | From | |
|---|---|---|---|
| Hailuo 2.3 Standard Text to Video | Prompt | $0.28 | Generate |
| Hailuo 2.3 Pro Text to Video | Prompt | $0.49 | Generate |
| Hailuo 2.3 Standard Image to Video | Image + prompt | $0.28 | Generate |
| Hailuo 2.3 Pro Image to Video | Image + prompt | $0.49 | Generate |
| Hailuo 2.3 Fast Image to Video | Image + prompt | $0.19 | Generate |
| Hailuo 2.3 Fast Pro Image to Video | Image + prompt | $0.33 | Generate |
| MiniMax H3 Text to Video | Prompt | $0.04 | Generate |
| MiniMax H3 Image to Video | Image + prompt | $0.04 | Generate |
| MiniMax H3 Reference to Video | Reference images + prompt | $0.15 | Generate |
| MiniMax H3 Video Edit | Video + prompt | $0.05 | Generate |
Frequently asked questions
Which Hailuo model should I use?
Start with MiniMax H3 if you need reference inputs, video editing, longer clips or many aspect ratios. Choose Hailuo 2.3 for physics-aware text and image to video, and the Fast tiers for quick image to video clips.
How long can the videos be?
MiniMax H3 generates from 3 to 15 seconds in one-second steps. Hailuo 2.3 Standard and Fast offer 6 or 10 seconds, and Fast Pro makes 6 second clips.
Which resolutions and aspect ratios are available?
Hailuo 2.3 Standard runs at 768p and Pro at 1080p. MiniMax H3 offers 480p, 540p, 768p and 1080p, with 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 and 9:21.
What can I use as references?
MiniMax H3 Reference to Video takes up to 9 images, 3 video clips and 3 audio tracks alongside your prompt, which helps keep characters and timing consistent.
How does MiniMax H3 Video Edit work?
Upload a video and describe what should change; reference images and audio are optional. You can switch native audio on or off for the result, and the output length follows the input unless you set one.
Can I use Hailuo through an API?
Every model in the table above has a REST API. Open a model page for the request schema and code samples; prices shown here update live.