MiniMax H3 Fast Image-to-Video API by MiniMax
MiniMax H3 Fast image-to-video: animate a first-frame image (optionally with a last frame) driven by a text prompt. Supports 480P, 5-15s.
MiniMax H3 Fast Image-to-Video är utvecklad av MiniMax. Atlas Cloud (som drivs av Atlas Cloud AI LLC) tillhandahåller åtkomst till modellen men äger den inte. Alla varumärken tillhör sina respektive ägare.
MiniMax H3 Fast Image-to-Video
MiniMax H3 Fast Image-to-Video brings a static image to life at the lowest cost and quickest turnaround in the H3 family. Provide a first-frame image — and, optionally, a last frame — plus a prompt describing the motion, and the model generates a complete 24fps 480P clip with audio that starts (and optionally ends) exactly on your images. Its speed makes it ideal for trying several motion directions before committing to a higher-resolution render.
Why Choose This?
-
Fastest, most economical tier Speed-optimized 480P generation — the quickest and cheapest way to animate an image with H3 quality.
-
Image-driven generation Animate any image with natural, controllable motion.
-
First & last frame control Set the opening frame, and optionally pin the closing frame for a precise transition.
-
Audio included Every clip is generated as complete audio-video at 24fps — no separate scoring or sound pass.
-
Aspect ratio from your image Automatically determined by the input image (always adaptive).
-
Selectable duration Produce 5–15s clips.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired motion and action |
| image | Yes | First frame of the video (public URL or Base64) |
| end_image | No | Last frame of the video (public URL or Base64) |
| resolution | Yes | Video resolution. Only 480P is available for the Fast model |
| duration | Yes | Duration of the generated video in seconds. Available options: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15. Default 8 |
| ratio | No | Aspect ratio of the generated video. For image-to-video the aspect ratio is determined by the input image and is always adaptive; passing any other value is ignored. |
| prompt_expansion | No | Enable AI prompt expansion via H3 Context-IR. When true, your prompt is first expanded into a rich, structured description (shot, soundscape, music) before generation, and an additional per-token Context-IR fee applies. Default false: the prompt is used as-is with no extra charge. |
| callback_url | No | HTTPS URL notified whenever the task status changes, so you can react to completion without polling. Requires a one-time verification handshake — see Task Status Callbacks below. |
Task Status Callbacks (callback_url)
When you supply a callback_url, the MiniMax server notifies it on every task status change, so you don't have to poll for the result.
- Verification handshake — right after the task is created, the server first sends a verification request to your URL containing a
challengefield. Your endpoint must return thechallengevalue unchanged, within 3 seconds, to complete verification. - Status pushes — once verification succeeds, the server sends a
POSTto your URL every time the task status changes. The push body has the same structure as the Query Task (task status) response.
Callback status values: queued, running, succeeded, failed, cancelled.
The callback_url must be a publicly reachable HTTPS endpoint.
How to Use
- Upload your first-frame image — the video will start from this image.
- (Optional) Upload a last-frame image — the video will end on this image.
- Write your prompt — describe the motion, camera movement, and action.
- Set duration — pick any length from 5s to 15s.
- Run — submit and download your video. The aspect ratio follows your input image automatically.
Best Use Cases
- Rapid Iteration — Test many motion directions quickly and cheaply before a final high-res render.
- Photo Animation — Bring portraits, landscapes, and product images to life.
- Start/End Transitions — Morph smoothly from one image to another.
- Marketing & Ads — Turn product photos into dynamic promotional videos.
Pro Tips
- Be specific about movement direction, speed, and camera angles.
- When using a last frame, keep the two images' aspect ratios close for a clean transition.
- Use high-quality source images for better video results.
- Describe environmental effects (wind, smoke, dust) for more immersive motion.
Notes
- Both prompt and first-frame image are required.
- The last-frame image is optional; when provided, the clip ends on it.
- Supported image formats: png, jpeg, jpg, webp. Ensure image URLs are publicly accessible.
- Supported durations between 5s and 15s, at 24fps with audio.
- Resolution is limited to
480P— 768P and 2K are not available on the Fast model. - Keyframe interpolation and multimodal references (reference image / video / audio) are not supported in this mode.
- Generation is asynchronous — submit, then poll for the finished video.
Related Models
- MiniMax H3 Fast Text-to-Video — Generate video directly from a text prompt at the same speed.
- MiniMax H3 Fast Reference-to-Video — Keep reference subjects consistent across the clip.
- MiniMax H3 Image-to-Video — The standard H3 model, with 2K output and reference-to-video support.
