MiniMax Hailuo / VIDEO MODEL
Animate a first frame with camera directions. Choose six or ten seconds at 768p, or six seconds at 1080p.
Generated videos are stored for 24 hours, then deleted. Download files you want to keep.
Your next take will appear here.Sample footage · Hailuo 2.3 workspace
No generated videos yet.
Your inputs are saved while you work.MEET HAILUO 2.3
MiniMax Hailuo 2.3 on EveryGen AI supports both text-to-video and first-frame image-to-video requests. Its current configuration offers six or ten seconds at 768p and six seconds at 1080p. Choose the input mode first: text defines a scene from words, while a first frame supplies the opening composition for an image-led shot.
In image mode, the aspect ratio comes from the uploaded frame rather than a separate ratio parameter sent to this route. Prepare the source image for the composition you want, then describe the movement without asking the model to redesign the subject. There is one image slot, with no ending frame or separate reference collection in this workspace.
THE POSSIBILITIES
Choose the input that fits your idea, then shape the motion. Clips below are local sample footage for the layout.
Describe who or what is in the scene, what moves and how the camera observes it. Keep the action manageable for the selected duration. A six-second gesture or a ten-second gradual move can answer different creative questions without turning the request into a complete edited sequence.
Use the resolution selector before choosing a duration; 1080p allows six seconds only.
Upload a first frame with the desired subject scale and horizontal or vertical composition. Explain how the scene should move after that opening. The route derives framing from the source image, so crop it before upload if its shape does not fit the intended destination.
An ending frame and multiple image references are not available in this Hailuo configuration.
At 768p, choose six or ten seconds. At 1080p, the workspace limits the request to six seconds and adjusts an incompatible duration when settings change. Compare the configured credit estimate for the complete setup, then review the whole result for subject detail and continuity.
This route has no generated-audio switch; do not treat a sound instruction as a separately supported audio parameter.
FROM IDEA TO A TAKE
A clear starting point, a focused brief and settings you can review before submitting.
Open Hailuo 2.3 in the generator above. Choose Text to video for a written scene or Image to video when you have an opening composition.
Write the subject, action, camera direction and lighting. In image mode, upload one opening frame; an ending frame is not supported here.
Choose 768p or 1080p output. 768p: 6 or 10 seconds; 1080p: 6 seconds. In image mode, framing comes from the source image. Review the estimate after changing a setting or adding a reference clip.
When generation is enabled, submit after reviewing the brief and content checks. Track the request in Recent takes. Review the full clip for subject details, continuity and sound, then download a useful result or change one part of the brief for the next take.
A STARTING POINT, NOT A SCRIPT
Load a brief with supported settings in the full workspace. Review it and add your own images or references where required.
A person sits in a quiet lounge near a warm lamp. The person looks up and turns gently toward the window. A steady medium composition, natural posture and a consistent background. One continuous movement with no extra people, written signs or scene cuts.
Start with six seconds; use ten seconds at 768p only if the action needs more room.
Use the uploaded image as the opening frame. The subject makes a small head turn while the camera moves gently closer. Keep the face, outfit and room details consistent. Preserve the source composition, avoid added objects and finish on a calm pose.
Crop the first frame to the intended format before uploading it.
PUT THE SHOT TO WORK
Start with the job the clip needs to do. Keep final editing and a full review in your workflow.
Use text when appearance can be described rather than anchored to an image. Make the movement and viewpoint readable in one short shot.
Start with one clean frame, preserve its composition in the brief and describe a small gesture. Check identity and background changes across the clip.
Prepare a vertical first frame for the image workflow. The source image's framing matters because the route does not receive a separate aspect-ratio field.
BEFORE YOUR NEXT TAKE
A cramped first frame leaves little room for movement. Choose a readable subject and enough surrounding space, with the intended horizontal or vertical crop. Do not rely on a ratio selector that this provider route does not accept.
Ten seconds is available at 768p, not at 1080p here. The workspace keeps these settings compatible, but you should still review the revised duration and quote after switching resolution.
THE SETUP
Every model has its own inputs and credit rules. Changing a setting refreshes your quote.
| Duration | 768p: 6, 10 seconds · 1080p: 6 seconds |
|---|---|
| Output sizes | 768p · 1080p |
| Frame inputs | One first frame |
| Additional references | 0 images · 0 videos · 0 audio files, where the mode supports them |
| Audio | No generated audio toggle |
FIXED CREDIT RULES
A 20-credit content-check allowance is included once per request. Match the rate below to your chosen output size.
| Resolution | Input | Rate |
|---|---|---|
| 768p | Text / supported images | 50 credits / output second |
| 1080p | Text / supported images | 74 credits / output second |
Rate version v8-fixed-2026-10-11. The final quote appears before submission. Paid generation is awaiting activation.
Compare plans and credit allowances →BEFORE YOU CREATE
Inputs, output settings and credit rules for this workspace.
Text to video is supported: describe a scene and its movement. One first frame is supported in image mode. There is no separate collection of appearance-reference images on this route.
768p supports 6 or 10 seconds. 1080p supports 6 seconds. The controls above use these same settings. A resolution selection describes the requested output and does not guarantee native detail or readable small text.
This configured route does not expose video or audio reference uploads. Put movement and sound directions in the prompt where supported. Compare Seedance 2.0 if your scene needs those reference types.
The credit table below the controls section lists this model's fixed rates for every supported output size. Some routes charge per request and others by duration. A content-check allowance is included once. Use Review credit estimate in the generator for the actual settings and uploaded reference duration before submitting.
This workspace does not expose a generated-audio switch for this route. Plan to add the final voice recording, effects or music in your editing workflow rather than depending on a soundtrack control that is not offered.
Prompts and image references are checked before submission. A rejection or unavailable check stops submission. These checks do not audit reference-video frames or audio tracks. Confirmed failed tasks release reserved credits once; an uncertain submission remains under review to avoid duplicate requests.
The current clips are local sample footage used to demonstrate the layout. They are not outputs from the displayed prompts, model benchmarks or evidence of a specific model's quality. Example prompts are editable starting points; image and reference examples require your own uploads.
FIND THE RIGHT FIT
Animate a first frame with camera directions. Choose six or ten seconds at 768p, or six seconds at 1080p.
768p / 1080p · Image to videoDevelop a shot from text or an image, then review the next take.
480p / 720p / 1080p · 2 input modesYOUR NEXT SCENE
Start with a brief. Choose the inputs. Review the settings.