Models

How to Use MiniMax H3 in ChatCut: 12 Tested Clips, Prompts and Credits

Fuxuan Guo
23 min read
How to Use MiniMax H3 in ChatCut: 12 Tested Clips, Prompts and Credits
Contents
  1. Key takeaways
  2. What you need before you start
  3. Step 1: Open Video Gen and pick MiniMax H3
  4. Step 2: Start with one action in text
  5. Step 3: Start on your image with a first frame
  6. Step 4: End on your image with a last frame only
  7. Step 5: Move between two images with first and last frames
  8. Step 6: Use a product photo and a music track as references
  9. Step 7: Borrow a camera move from a video
  10. Step 8: Render at 2K once the shot works
  11. MiniMax H3 vs H3 Max: the same prompt on both
  12. Step 9: Trim the clip and edit it into a video
  13. What our 12 clips cost
  14. Review every take
  15. MiniMax H3 troubleshooting
  16. Next steps

To use MiniMax H3 in ChatCut, switch the AI composer to Video Gen, pick MiniMax H3, choose text, Frames or References under Video settings, set a length of 4 to 15 seconds at 768p or 2K, write the shot with its sound, check the credit estimate and send. We ran each of those routes on November 20, 2026: four text prompts, a first frame, a last frame on its own, first and last frames together, a product photo with a music track, a camera move borrowed from a drone clip, a 2K render, and the same prompt on H3 Max. Below are every prompt, clip, setting and charge (33.03 credits for all 12 clips) and what to check in each take.

MiniMax released H3 on July 31, 2026. Its earlier video models were branded Hailuo (Hailuo 02, Hailuo 2.3), and Hailuo AI is still the name of MiniMax’s consumer app; H3 drops the prefix. For specs and more sample clips, see the MiniMax H3 model page.

Key takeaways

  • Text alone gets the action. Our first text prompt produced the back spin, the one-handed freeze and the water spray we asked for: 8 seconds at 768p for 3.08 credits.
  • Frames fix the composition. H3 takes a first frame, a last frame on its own, or both, and the clip takes the shape of your image.
  • References need a job. Label each file in the prompt (@Image1, @Audio1, @Video1) and say what it controls. Frames and references can’t be combined in one request.
  • Check the subject in wide shots. Our perfume bottle matched the photo in the close-up but came out slimmer in the opening wide shot.
  • Know the per-second rate. In our tests 768p cost 0.384 credits a second, 2K cost 0.625, and H3 Max at 480p cost 0.24. A reference video is billed by the second too.

What you need before you start

  • ChatCut on a paid plan. Video generation in ChatCut needs a paid plan, and each clip uses credits; the estimate shows beside Send before anything is charged. H3 is in Video Gen in the web editor and in ChatCut Desktop.
  • One shot in mind. A subject, one action, a camera move, and how the shot ends.
  • Your inputs, if any. A still for the first or last frame, or images, short video clips and audio to use as references. Use media you made or have the rights to.

MiniMax H3 and MiniMax H3 Max sit side by side in the model menu. The differences that change what you can do:

MiniMax H3MiniMax H3 Max
Clip length4–15 s5–15 s
Resolution768p or 2K480p or 768p
FramesFirst, last, or both; a last frame can stand aloneFirst, or first and last; a last frame needs a first frame
ReferencesUp to 9 images, 3 videos and 3 audio clips, 12 files in allNone: text, a first frame, or first and last frames only
What we paid per second0.384 credits at 768p, 0.625 at 2K0.384 credits at 768p, 0.24 at 480p

Step 1: Open Video Gen and pick MiniMax H3

  1. Open a project and switch the AI composer from Agent to Video Gen.
  2. Click the model name below the composer and choose MiniMax H3 (or MiniMax H3 Max).
  3. Open Video settings. Under Input, choose Frames (leave both slots empty for text only) or References, then set Aspect ratio, Resolution and Duration.
  4. Write the prompt, check the credit estimate beside Send, and select Send message.
  5. Follow progress in the Media Pool, then drag the finished clip to the timeline.

You can also stay in Agent mode, attach your files and describe the shot in plain words; the Agent picks the inputs and writes the prompt. The AI video generation docs list every model’s controls.

Step 2: Start with one action in text

Write the subject, one action, the camera and the sound. H3 generates audio with every clip, so the sound line is part of the prompt, not an afterthought.

Try this promptOpen in ChatCut
A street dancer in a yellow raincoat breakdances on a wet basketball court at night under a single floodlight. He spins on his back, kicks into a windmill, flips up into a one-handed freeze, then pops to his feet and lands a final pose as rain sprays off his coat. The camera circles low around him at ground level; puddles reflect the light. Fast, precise body movement with correct physics; water splashes from every move. Cinematic, high contrast, shallow depth of field. Sound: heavy rain, sneakers squeaking, a hip-hop beat echoing off the walls. No text.
Demo
Text only. MiniMax H3 in ChatCut, 16:9, 8 s, 768p, 3.08 credits. Turn the sound on.

What to check: the back spin, the one-handed freeze and the spray off the coat are all there, and he finishes on his feet. That is about as many moves as we would put in eight seconds; if one goes missing, cut the list down rather than adding adjectives. Turn the sound on and listen for each sound you named.

Three more text-only shots

These test fire, water and a face. Each is 16:9, 8 seconds at 768p, and cost 3.08 credits.

Fire, then a push in to the plate.

Try this promptOpen in ChatCut
A chef in a busy restaurant kitchen tilts her pan and a tall burst of flame erupts, lighting her face orange; she tosses the food high, catches it in the pan and slides it onto a white plate in one motion. Steam and a few sparks drift through warm tungsten light; cooks move past in the background. The camera pushes in slowly from a medium shot to a close-up of the plate. Realistic fire, oil and steam. Sound: sizzling oil, the whoosh of the flame, clattering pans, kitchen chatter. No text.
Demo
MiniMax H3 in ChatCut, 16:9, 8 s, 768p, 3.08 credits.

What to check: the flame bursts in the first second, the food goes onto the plate, and the camera ends close on the dish. We could not see a clear toss and catch. In eight seconds, one big action and a clear ending is safer than three actions in a row.

Underwater, with a large animal close to the lens.

Try this promptOpen in ChatCut
Underwater documentary. A freediver in a black wetsuit and long fins glides down beside a huge whale shark in clear blue water, sunbeams flickering through the surface above. Small silver fish scatter as the shark turns slowly toward the camera, its spotted skin passing close to the lens; the diver keeps a respectful distance. Slow, smooth tracking shot alongside them. Sound: muffled water, a deep calm hum, bubbles. No text.
Demo
MiniMax H3 in ChatCut, 16:9, 8 s, 768p, 3.08 credits.

What to check: the spotted skin slides past the lens, the diver stays at a distance, and the fish scatter at the start. This was the cleanest of the four text clips.

A face in close-up.

Try this promptOpen in ChatCut
Intimate drama at dusk. An old fisherman sits on a wooden dock reading a handwritten letter, the sea glowing orange behind him. His eyes fill with tears, then a slow smile spreads across his weathered face; he lowers the letter, looks out to sea and says quietly, "She's coming home." Natural skin texture, subtle micro-expressions, warm low sun on his face. The camera pushes in slowly from a medium shot to a close-up. Sound: gulls, small waves against the dock, his quiet voice. No subtitles, no music.
Demo
MiniMax H3 in ChatCut, 16:9, 8 s, 768p, 3.08 credits.

What to check: he lowers the letter and the camera pushes in from a medium shot to a close-up of his face. We asked for one quiet line; the soundtrack of our take is quiet and we could not make out the words, so listen before you build an edit on it, and record the line separately if the wording has to be exact.

Step 3: Start on your image with a first frame

In Video settings → Input, choose Frames and drop your image on First frame. The prompt then only has to describe what happens next. MiniMax’s prompt-writing guide suggests the same order for this mode: anchor on what is in the image, then the action, then how it develops.

Try this promptOpen in ChatCut
Start exactly on this frame. The woman in the yellow raincoat keeps walking the corgi along the wet London pavement; the corgi trots ahead and looks back up at her; she laughs and pulls her hood back as the rain eases. A red double-decker bus passes in the background and reflections ripple in the puddles. The camera follows at their pace. Sound: rain on the pavement, footsteps, the bus going by.
Demo
First frame. MiniMax H3 in ChatCut, 3:4 (from the image), 5 s, 768p, 1.92 credits.

What to check: the clip opens on our image, a woman in a yellow raincoat walking a corgi past a red phone box, then she pulls her hood back while the corgi trots ahead through the puddles. The output is 3:4 because the image is: in frame mode H3 takes the aspect ratio from the frame, so crop your image to the shape you need before you upload it.

Step 4: End on your image with a last frame only

H3 can take a last frame with no first frame. It then works out an opening that leads into your picture, which suits a reveal that has to land on one exact shot. (H3 Max needs a first frame whenever you add a last one.) Say where the shot should start; otherwise H3 has to guess.

A small harbour in morning sun with blue and red wooden fishing boats moored in calm water below pastel houses on a hill.
The last frame we gave H3: a harbour image made with Nano Banana in ChatCut.
Try this promptOpen in ChatCut
End exactly on this frame of the harbour. The clip opens on a low close-up of coiled ropes and the bow of a blue wooden fishing boat bobbing on the water, then the camera rises and pulls back over the moored boats to reveal the whole harbour and the pastel houses on the hill in the morning sun. Sound: water lapping, gulls, a distant boat engine.
Demo
Last frame only. MiniMax H3 in ChatCut, 3:2 (from the image), 5 s, 768p, 1.92 credits.

What to check: the clip opens on the coiled rope and the blue boat, rises over the moored boats and settles on our harbour image. Compare the final frame with your image before you cut to the next shot.

Step 5: Move between two images with first and last frames

Give H3 the start and the end, and describe the change in between. MiniMax’s guide puts it as a path from the first frame through visible intermediate changes to the last.

A street corner on a summer afternoon: a yellow building with green striped awnings, outdoor tables, plants on the roof terrace and blue shutters next door.
First frame: a real photo of a street corner.
The same street corner on a snowy blue evening, with snow on the awnings, tables and rooftop plants and warm light in the shop windows.
Last frame: the same photo edited into a snowy evening with Nano Banana.
Try this promptOpen in ChatCut
One continuous locked-off shot of the same street corner. Start on the first frame on a summer afternoon; snow begins to fall and settles on the rooftop plants, awnings, tables and pavement while the light shifts to blue evening and the shop windows light up warm, ending exactly on the last frame. Sound: summer street noise fading into quiet snowfall and a soft wind.
Demo
First and last frames. MiniMax H3 in ChatCut, 5:4 (from the images), 5 s, 768p, 1.92 credits.

What to check: snow starts falling and settles on the plants, awnings and tables, the light turns blue, the shop windows light up, and the shot lands on the last frame. We kept both frames on the same framing and asked for a locked-off shot, so H3 only had to change the weather and the light.

Step 6: Use a product photo and a music track as references

References guide how things look, move or sound without fixing a frame; they work on H3, not H3 Max. In Video settings → Input, choose References and add the files in order, then name each one in the prompt (@Image1, @Video1, @Audio1) and say what it controls. One H3 request takes up to 9 images, 3 videos and 3 audio clips, 12 files in all; each video or audio clip must run 2 to 15 seconds, with 15 seconds per type in total. The references guide covers formats.

A perfume bottle on black: a fluted red cap on a wide blue glass body with a moon, stars and trees inside the glass.
@Image1, a real product photo. @Audio1 was an 8-second music bed.
Try this promptOpen in ChatCut
Perfume commercial cut to music. @Image1 is the exact perfume bottle: a fluted red cap on a blue glass body with a moon, stars and trees inside the glass. Use @Audio1 as the soundtrack and cut on its beat. The bottle stands on black water; drops fall around it and send rings across the surface on each beat, then the camera glides in close as blue light glows through the glass. Keep the bottle's shape, cap and the scene inside the glass the same in every shot. No text, no logos, no hands.
Demo
Image and audio references. MiniMax H3 in ChatCut, 16:9, 6 s, 768p, 2.31 credits. Turn the sound on.

What to check: the close-up in the second half matches the photo well: the fluted red cap, the blue glass, and the moon and trees inside it, lit from within. The opening wide shot does not. Drops fall and ring the water as asked, but the bottle there is slimmer than the real one. Check the product’s proportions in every shot, not just the close-ups; if a wide shot drifts, trim it on the timeline or generate the close-up on its own.

The clip cost 2.31 credits, about what 6 seconds of text-only video costs at 768p. On H3 the audio reference is free, and so are the first five images.

Step 7: Borrow a camera move from a video

Add a video as a reference and say it supplies the camera movement only. Then describe a new scene, and tell H3 not to copy the reference’s landscape.

An aerial view at dusk of a rocky headland reaching into a turquoise lake, with hills behind.
A frame from @Video1, an 8-second real drone clip that drifts slowly around a headland.
Try this promptOpen in ChatCut
Copy only the camera movement of @Video1: a slow, high aerial drift and turn around a headland. New scene: the same slow aerial move over a red sandstone canyon at sunset with a green river winding through it, long shadows across the rock. Do not copy the landscape or colours of @Video1. Smooth drone footage. Sound: wind, a distant hawk call. No text.
Demo
A video reference for the camera move. MiniMax H3 in ChatCut, 16:9, 5 s, 768p, 5.00 credits.

What to check: a slow, high drift over a red canyon bend with a green river, and none of the lake or its colours. The move is as gentle as the reference’s; pick a reference that already moves the way you want.

This was the most expensive 768p clip in our set. H3 bills a reference video by the second at the output rate, so the 8-second reference plus the 5-second clip came to 5.00 credits. Trim a reference down to the move you need (at least 2 seconds) before you add it.

Step 8: Render at 2K once the shot works

Set Resolution to 2K for a 2560×1440 clip at 16:9. 2K cost 0.625 credits a second in our test against 0.384 at 768p, so settle the prompt at 768p first. A 2K request is a new generation: expect a new take, not your 768p clip at a higher resolution.

Try this promptOpen in ChatCut
Macro nature shot. A green chameleon on a mossy branch slowly rotates one turret eye toward the camera, then its skin shifts from green to orange in a wave along its body; every scale and ridge is sharp. Dark jungle background, soft studio light from the left, shallow depth of field. Sound: soft jungle ambience, a faint insect buzz. No text.
Demo
2K. MiniMax H3 in ChatCut, 16:9, 5 s, 2560×1440, 3.12 credits.

What to check: at 2K, look at fine texture at full size. Here the scales and the crest stay sharp while the colour moves from green to orange along the body.

MiniMax H3 vs H3 Max: the same prompt on both

H3 Max is a separate model in the same menu; fal, which built it, describes it as a post-trained version of H3. In ChatCut it runs 5 to 15 seconds at 480p or 768p, with no 2K. It works from text, a first frame, or first and last frames (a last frame needs a first frame); it does not take reference images, videos or audio, so steps 6 and 7 are H3 only. We ran only text prompts on H3 Max.

We sent the step 2 breakdance prompt to both, 16:9, 8 seconds at 768p:

Demo
MiniMax H3, 8 s, 768p, 3.08 credits.
Demo
MiniMax H3 Max, same prompt, 8 s, 768p, 3.08 credits.

What differed: H3 stayed low and close on the spins and the freeze. H3 Max framed it wider and darker, with the dancer kicking off the court into a one-handed hold before he lands. The price was the same at 768p. One pair of takes can’t rank the two models; it does show that the same prompt gives a different shot, so if you like a framing, stay on that model for the retakes.

H3 Max also offers 480p, the cheapest setting we used: this 6-second vertical clip cost 1.44 credits.

Try this promptOpen in ChatCut
Vertical social clip. Overhead close-up of a barista pouring steamed milk into a cup of espresso; a white tulip pattern blooms in the crema, then she pulls the jug away and slides the cup toward the camera across a wooden counter. Warm morning light, shallow depth of field. Sound: milk hissing, a cup clinking, quiet cafe chatter. No text.
Demo
MiniMax H3 Max in ChatCut, 9:16, 6 s, 480p, 1.44 credits.

What to check: the pour, the pattern blooming in the crema and the cup sliding toward the camera all happen. We asked for a tulip and got a leaf-shaped rosetta. A 480p draft is a cheap way to find out whether a detail like that holds before you pay for 768p.

Step 9: Trim the clip and edit it into a video

A generated clip is a shot, not a finished video. Drag it from the Media Pool to the timeline, trim the start and the end, and place it beside your other shots. Add editable text for exact names or a call to action, adjust the generated audio, add a voiceover or music if you need them, and review the whole sequence before you export.

A good 8-second take may give you three usable seconds; keep the part that serves the cut. Because generation and editing share one project, a retake is one prompt away instead of an export and re-import.

Generate the shot with MiniMax H3 and cut it on the same timeline.Download DesktopDownload for macOSDownload for WindowsTry Now

What our 12 clips cost

ClipModelSettingsCredits
Breakdancer (text)H316:9, 8 s, 768p3.08
Flambé (text)H316:9, 8 s, 768p3.08
Whale shark (text)H316:9, 8 s, 768p3.08
Fisherman (text)H316:9, 8 s, 768p3.08
Raincoat and corgi (first frame)H33:4, 5 s, 768p1.92
Harbour (last frame only)H33:2, 5 s, 768p1.92
Street corner (first and last frames)H35:4, 5 s, 768p1.92
Perfume (image and audio references)H316:9, 6 s, 768p2.31
Canyon (8-second video reference)H316:9, 5 s, 768p5.00
ChameleonH316:9, 5 s, 2K3.12
Breakdancer (same prompt)H3 Max16:9, 8 s, 768p3.08
Latte artH3 Max9:16, 6 s, 480p1.44
Total33.03

All 12 clips cost 33.03 credits, about $8 at a credit’s $0.25 face value. Every take is charged, including the ones you throw away, so test at 768p (or 480p on H3 Max) and change one thing per retry.

Review every take

CheckAsk yourself
SubjectDoes the same person or product stay recognizable, in wide shots as well as close-ups?
ActionDoes each action you asked for begin, finish, and happen in the right order?
ContactDo hands, tools and objects meet plausibly?
CameraDoes the camera move only as requested?
SoundAre the sounds you named there, and does any speech say what you wrote?
EndingCan the final moment cut cleanly into the next shot?

MiniMax H3 troubleshooting

ProblemWhat we sawFix
A product changes shape in a wide shotThe perfume bottle slimmed down in the opening wide shotKeep the product large in frame, generate the close-up alone, or use the photo as a first frame
An action goes missingThe chef’s toss and catch didn’t showOne big action per clip, and say how it ends
A small detail comes out differentA tulip became a rosettaDescribe the detail more precisely and test it on a cheap draft
Speech is too quiet to useThe fisherman’s line was hard to hearListen before you edit; record the line separately if the words matter
The camera barely movesThe video-referenced drift was gentleChoose a reference that already moves the way you want
Frames and references won’t go togetherThey are separate input familiesFrames for an exact first or last picture; references for look, motion and sound
H3 Max won’t take a lone last frame or a referenceIt works from text and frames only, and a last frame needs a first frameAdd a first frame, or switch to H3 for references and last-frame-only shots
Music you didn’t wantSound wasn’t describedDescribe ambience and music separately, write “no music”, or mute it on the timeline

Next steps

Start with one text prompt at 768p, check it against the list above, and add a frame or a reference only when you need control that text can’t give. The MiniMax H3 model page has more clips and the full specs. To change or continue a clip you already have, use a model with Edit video and Extend video modes, such as Seedance 2.5 Flash or Gemini Omni; for a single take longer than 15 seconds, use Seedance 2.5.

Three ways to try ChatCut
Edit local files on your computer For long footage, screen recordings and 4K exports. macOS and Windows. Download DesktopDownload for macOSDownload for WindowsOpen in your browser
On a computer, download ChatCut Desktop.
Start in your browser Free plan, nothing to install. The editor opens with this prompt: Generate an 8-second 16:9 video with MiniMax H3 at 768p: a street dancer in a yellow raincoat breakdances on a wet basketball court at night under a single floodlight, water spraying off every move. Sound: heavy rain, sneakers squeaking, a hip-hop beat. Try this prompt
Already using an AI agent? Send this one message to the agent you use.
Read ChatCut.io/desktop to install ChatCut
Send it in a new Claude Code conversation. Setup guide

Frequently asked questions

How do I use MiniMax H3 in ChatCut?
Switch the AI composer to Video Gen, choose MiniMax H3 in the model menu, set the input, aspect ratio, resolution and duration under Video settings, write the prompt and send it. The clip appears in the Media Pool, ready to drag onto the timeline. You can also describe the shot to the ChatCut Agent and let it set things up.
Is MiniMax H3 free in ChatCut?
No. Video generation in ChatCut needs a paid plan, and each clip uses credits; the editor shows the estimate before you send. On November 20, 2026, a 5-second 768p H3 clip cost us 1.92 credits and an 8-second one 3.08.
Is MiniMax H3 the same as Hailuo?
Hailuo was the brand of MiniMax's earlier video models, such as Hailuo 02 and Hailuo 2.3, and Hailuo AI is MiniMax's consumer app. H3, released on July 31, 2026, is the newer model and drops the Hailuo name. ChatCut lists it as MiniMax H3.
Does MiniMax H3 generate sound?
Yes. Every clip in this guide came with an audio track generated from the prompt's sound line. Describe ambience, effects and music separately, and add an audio reference if you want a specific track.
How long and how sharp can MiniMax H3 clips be?
H3 makes 4- to 15-second clips at 768p or 2K (2560x1440 at 16:9). H3 Max makes 5- to 15-second clips at 480p or 768p. For longer videos, join clips on the timeline.
What is the difference between MiniMax H3 and H3 Max?
In ChatCut, H3 takes text, frames (including a last frame on its own) or up to 12 reference images, videos and audio clips, at 768p or 2K. H3 Max takes text, a first frame, or first and last frames, at 480p or 768p, with no references and no 2K. fal, which built H3 Max, describes it as a post-trained version of H3. At 768p both cost us 0.384 credits a second.
Can MiniMax H3 edit or extend an existing video?
Not in ChatCut. H3 makes new shots from text, frames or references. ChatCut's Edit video and Extend video modes are on Seedance 2.5, Seedance 2.5 Flash and Gemini Omni 1.1 Flash.
Do I need a MiniMax API key?
No. You pick MiniMax H3 in ChatCut and pay with ChatCut credits; there is no separate MiniMax account or key to set up.

Checking your footage...

Less editing. More creating.

Download ChatCut Desktop free and make your first video today.

Download Desktop Download for macOS Download for Windows Try it for free