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 Fast workspace
No generated videos yet.
Your inputs are saved while you work.MEET HAILUO 2.3 FAST
MiniMax Hailuo 2.3 Fast is an image-to-video route in the EveryGen AI workspace. It requires one first-frame image; a written prompt on its own is not a complete request. Upload the composition you want to animate, then describe the subject movement or camera direction that should follow.
The output choices are six or ten seconds at 768p, and six seconds at 1080p. The route takes its framing from the first image rather than a separate aspect-ratio field. Its lower configured credit rate than Hailuo Standard can be useful when comparing image-led ideas, but the Fast name does not establish a guaranteed wait time or success rate.
THE POSSIBILITIES
Choose the input that fits your idea, then shape the motion. Clips below are local sample footage for the layout.
Choose a picture that already contains the subject, setting and framing you need. Upload it before reviewing the estimate. The prompt should describe the next movement, not a different person or location that conflicts with the source. A written idea without an image belongs in a text-capable model instead.
One opening image is supported; there is no last-frame or multiple-reference upload workflow here.
Start with a small gesture, a gentle approach or a lateral move. Say which parts of the scene should remain stationary and keep the subject's important details in view. Review the result for changed faces, clothes, object shapes and background relationships throughout the movement.
Reference guidance does not guarantee exact preservation of the uploaded picture.
Choose 768p when a six- or ten-second request fits the idea, or 1080p for the supported six-second setup. The workspace removes the ten-second option at 1080p. Prepare the source crop for the intended format, because no separate aspect-ratio parameter is sent to this Hailuo route.
Review the final estimate whenever you change resolution or duration.
FROM IDEA TO A TAKE
A clear starting point, a focused brief and settings you can review before submitting.
Hailuo 2.3 Fast requires an image. Choose a clear subject and crop the source to the composition you want to animate. Upload it as the first frame in the generator above.
Explain what moves, how the camera behaves and which parts of your source image should stay stable. One visible gesture or a gentle camera move gives you a specific result to review.
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.
Use the uploaded photograph as the first frame. The person turns slightly toward the camera and smiles, with a small natural shoulder movement. Keep the face, clothing and background consistent. A stationary medium view, no added people, props, lettering or cuts.
Upload a first frame before estimating; Hailuo Fast does not support a text-only request.
Begin with the supplied image. Make a slow camera approach while the subject remains mostly still, with subtle natural movement. Preserve the source image's proportions, outfit and environment. Let the final composition settle, with no new objects or changes of location.
Use a source image with enough room around the subject for the requested camera move.
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 a sharp, unobstructed first frame and describe one head turn or expression. Inspect changes to identity before keeping the clip.
Animate a scene whose framing is already approved. Keep the prompt focused on movement rather than adding new subjects or redesigning the environment.
Crop your first image for a vertical layout, then describe motion that remains inside it. Check the complete clip for unintended reframing.
BEFORE YOUR NEXT TAKE
Hailuo Fast requires an uploaded image. If you are describing a new scene without assets, open Hailuo 2.3 Standard or another text-to-video model. Loading a prompt cannot replace the required first frame.
The image establishes the framing sent to this route. Crop and inspect it before upload, especially for vertical work. A motion prompt should not assume the model will preserve important details that are already cut off in the first image.
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 | First frame required | 26 credits / output second |
| 1080p | First frame required | 44 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.
This route requires an opening image; a text-only request is not supported. 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 · 2 input modesCreate a shot from text or a first frame with a single image reference.
480p / 720p / 1080p · 2 input modesYOUR NEXT SCENE
Start with a brief. Choose the inputs. Review the settings.