AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.085 per second of video
MiniMax's Hailuo variant for sharp 1080p video clips up to 10 seconds. Text-to-video and image-to-video, no sound. Available on every Craze plan, including Free.
At 1080p, Hailuo 02 Pro is sharp enough for large displays, hero shots, and quality-conscious work.
No automatic sound generation means you control exactly what the viewer hears.
Start from a reference image and let Hailuo extend it into motion.
Hailuo 02 Pro supports 6-second and 10-second clips only.










Craze creatively jams, researches and plans with you.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| MiniMax Hailuo 02 ProMiniMax | Seedance 2.5ByteDance Seed Team | Seedance 2.0ByteDance Seed Team | Seedance 2.0 FastByteDance Seed Team | |
|---|---|---|---|---|
| Makes | Text + Image to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video |
| Quality | Up to 1080p | Up to 1080p | Up to 4K | Up to 720p |
| Length | Up to 10s per clip | Up to 30s per clip | Up to 15s per clip | Up to 15s per clip |
| Sound | — | Generated with the picture | Generated with the picture | Generated with the picture |
| From | $0.085 per second of video | $0.114 per second of video | $0.075 per second of video | $0.06 per second of video |
| Task | Inputs | Resolution | Length | Aspect ratios | Sound |
|---|---|---|---|---|---|
| Text to video | Text prompt | 1080p | 6, 10 s | Follows the input | None |
| Image to video | First frame, Last frame | 1080p | 6, 10 s | Follows the input | None |
$0/ month
$19/ month
$59/ month
$199/ month
MiniMax Hailuo 02 Pro is the silent, 1080p video generation specialist. When you need sharp, broadcast-quality video for a short burst, Hailuo delivers clarity without compromise. The deliberate absence of sound generation is a feature: it gives you complete control over what the viewer hears, from voiceover timing to music selection to foley detail.
Hailuo 02 Pro is the 1080p specialist. When you need sharp, broadcast-quality video for a short burst, Hailuo delivers clarity without compromise. The silent output is deliberate: it lets you add your own sound design, music, and voiceover exactly when you want it. For creators who prioritize audio post-production as much as video, that control is essential.
At 1080p, Hailuo 02 Pro is sharp enough for large displays, hero shots, and quality-conscious work. The clarity is noticeable next to lower-resolution models. When your deliverable goes to a large screen, a commercial break, or a high-quality publication, 1080p is the baseline expectation.
No automatic sound generation means you control exactly what the viewer hears. Add a voiceover in post, layer in music, or use natural sound from your references. That freedom is more valuable than built-in sound when you're building a polished edit. Many professional workflows require independent audio post-production, and Hailuo's silent output integrates perfectly into that pipeline.
Start from a reference image and let Hailuo extend it into motion. That gives you precise framing and character setup before the model generates. You can nail the composition in the first frame before the model adds motion, ensuring that the opening shot matches your vision exactly.
Hailuo 02 Pro supports 6-second and 10-second clips only. That constraint is actually useful: you know the exact duration before generation, which makes planning and pacing simpler. You can build your edit structure around those fixed lengths without unexpected surprises.
Hailuo 02 Pro does one thing: generates high-quality 1080p silent video in two fixed lengths. It doesn't handle audio, references, or variable lengths. That simplicity keeps the interface clean and the generation reliable.
Straightforward workflow with sharp output.
Specific prompts help. "A close-up of a hand holding a coffee cup, pulling back to reveal a sunlit office, warm morning light" is more useful than "coffee scene." The more specific your direction, the closer the generation matches your vision.
You pay per second of video. A 6-second clip and a 10-second clip have fixed prices per length. $0.085 per second of video Use the calculator on this page to confirm the price for your chosen length. The per-second cost is straightforward: choose your duration, see the price.
When the most important moment of your video needs to be sharp and clear, Hailuo's 1080p delivers that clarity. Use it for the reveal, the closeup, the dramatic moment that holds the shot.
Product launches, brand films, and high-end commercial work where 1080p is the minimum acceptable resolution. The silent output means you can add voiceover and music in post without worrying about conflicting AI-generated sound.
Generate hero moments at broadcast quality and intercut with live footage or other models. The silent output pairs well with the music track and any voiceover or dialogue.
For explainer videos, tutorials, and narrative work where your voiceover is the star. Hailuo's silent generation lets you time the narration perfectly without AI-generated sound interfering. Your voiceover can lead the pacing, and the video follows.
Image-to-video lets you nail the composition before the model adds motion. Useful for commercials where every frame matters, or when you have a storyboard and need the generated footage to match your boards.
When sound design is a core part of your creative vision (foley, ambient audio, or carefully layered soundscapes), Hailuo's silent output gives you a clean canvas to build from. The video won't have competing AI-generated audio to work around.
MiniMax H3 generates up to 15 seconds with always-on stereo sound, at multiple resolutions. Hailuo 02 Pro generates 6 or 10 seconds silent at 1080p. Choose H3 for longer clips with sound. Choose Hailuo 02 Pro for 1080p silent video and audio post-production control.
H3 Max generates up to 15 seconds at 480p, 768p, or 1080p with sound. Hailuo 02 Pro generates 6 or 10 seconds silent at 1080p only. Choose H3 Max for longer clips with sound. Choose Hailuo 02 Pro for silent video with precise audio control.
Describe what you want the way you would brief an editor, and Craze plans the shots and writes the MiniMax Hailuo 02 Pro prompts for you. Every Craze plan, including Free, runs MiniMax Hailuo 02 Pro and every other media model, and Craze can use a different one for each job. Each video lands on an editable timeline with your cuts, captions and music, ready to export as MP4. Generations come out of your plan's monthly credits, from $0.085 per second of video, with top-ups when you need more.
Hero shots and key moments: When the most important moment of your video needs to be sharp and clear, Hailuo's 1080p delivers that clarity. Product and brand work: Product launches, brand films, and high-end commercial work where 1080p is the minimum acceptable resolution. Music video key frames: Generate hero moments at broadcast quality and intercut with live footage or other models. Voiceover-driven content: For explainer videos, tutorials, and narrative work where your voiceover is the star.
MiniMax Hailuo 02 Pro generates 1080p video clips from text prompts or images. It supports clips from 6 to 10 seconds, with no sound generation.
MiniMax announced and released Hailuo 02 on June 18, 2025.
1080p, a sharp, broadcast-ready resolution suitable for hero shots and high-detail content.
6 or 10 seconds. Choose the length you need when you set up the generation.
No. Hailuo 02 Pro generates silent video. Add music, voiceover, or sound design in the edit.
Yes. Hailuo 02 Pro supports image-to-video, so you can use a reference image as the first frame.
$0.085 per second of video. Check the calculator on this page to estimate a specific length.
every Craze plan, including Free.
ByteDance Seed Team
From $0.114 per second of video
ByteDance Seed Team
From $0.075 per second of video
ByteDance Seed Team
From $0.06 per second of video