happyhorse-1.1/image-to-video
Animate a still photo into smooth 720P or 1080P video from one prompt.
Minimax H3 Image to Video is MiniMax's H3-series model for turning one picture into moving footage. You hand it the opening frame and describe what should happen; the model resolves motion, camera behavior, and scene development, then renders at 768p or 2K.
Because the first frame is pinned by your upload, subject identity, wardrobe, palette, and framing carry through the clip. Minimax H3 Image to Video therefore fits work where the look is settled and only movement is missing.
768p for cheaper drafts or 2k when faces, packaging text, and fine texture need to survive a full-screen crop.These are the live fields for Minimax H3 Image to Video on this page.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| image * | Yes (*) | string (URL) | Sample first frame | 256-5760 px per side, aspect ratio 0.4-2.5 | Opening frame that anchors subject, composition, and style. |
| prompt * | Yes (*) | string | Sample motion brief | 1-7000 characters | What should move, how the camera behaves, how the scene develops. |
| last_image | No | string (URL) | None | Same image constraints as image | Closing frame used to steer where the clip ends. |
| duration * | Yes (*) | integer | 5 | 4-15 | Clip length in whole seconds. |
| resolution * | Yes (*) | string | 768p | 768p, 2k | Output resolution tier. |
Minimax H3 Image to Video bills on resolution and the length of the finished clip:
| Resolution | Price per second | 5s | 10s | 15s |
|---|---|---|---|---|
| 768p | $0.09 | $0.45 | $0.90 | $1.35 |
| 2K | $0.145 | $0.725 | $1.45 | $2.175 |
1) Upload the opening frame — Pick an image where the subject reads clearly and the composition matches the shot you want.
2) Write the motion brief — Say what moves, how fast, and what the camera does. Minimax H3 Image to Video answers to verbs and camera language, not adjective lists.
3) Add a closing frame (optional) — Supply a last image when the ending matters, and keep it compatible with the first frame.
4) Set the length — Start at 5 seconds while tuning wording, then extend toward 15 once the motion behaves.
5) Choose the resolution — Use 768p for drafts; switch to 2k for final deliveries that need more detail.
6) Generate — Submit and review the Minimax H3 Image to Video result at full size.
7) Iterate one variable at a time — Swap the prompt, image, duration, or resolution separately so you can tell what changed the take.
When Minimax H3 Image to Video is not the right fit, these are worth a pass:
Animate a still photo into smooth 720P or 1080P video from one prompt.
Transform images into motion-rich clips with Hailuo 2.3's precise control and realistic visuals.
Prompt-driven song creation with 44.1 kHz WAV control and section editing
Cinematic 4K reference-to-video at $0.47 per second of output.
Transforms reference clips into 1080p short videos with precise motion and voice alignment.
Generate clips with fluid motion and audios for creatives
Minimax H3 Image to Video takes a still image plus a written motion brief and returns a 768p or 2K video clip. It is built for turning artwork, product photography, or a rendered frame into a moving shot without rebuilding the scene in a 3D or compositing tool. The uploaded image fixes the opening frame, so the subject and framing you already approved carry into the clip.
Besides the required first frame, Minimax H3 Image to Video accepts an optional last image that guides how the clip ends. The model works out the movement between the two stills instead of drifting toward an arbitrary final state. Keep the two images visually compatible in lighting, palette, and framing, or the transition will look forced.
Output resolution is selectable as 768p or 2k, and duration is selectable from 4 to 15 seconds in whole seconds. Shorter clips are the practical choice while you are still testing prompt wording with Minimax H3 Image to Video, and longer clips give a scene room to develop. Check the parameter panel on this page for the exact values currently exposed.
The source image should measure between 256 and 5760 pixels on each side with an aspect ratio between 0.4 and 2.5, and the prompt accepts 1 to 4000 characters. Minimax H3 Image to Video does not recompose a poorly cropped subject, so supply an image that already matches your intended framing. Limits may vary by mode or provider settings, so confirm against the live panel.
Describe what physically moves first, then the camera behavior, then lighting and mood. Minimax H3 Image to Video responds better to concrete verbs and named camera moves such as a slow push-in or an orbit than to stacked adjectives. Avoid mixing two competing visual styles in one prompt, since the result tends to average them out.
Text-to-video decides the subject, composition, and style from scratch, which makes it hard to hit an approved look twice. Minimax H3 Image to Video removes that variable by locking the opening frame to your upload, which suits product shots, character work, and campaign material where the art direction is already signed off. It is a narrower tool by design, with a short input list and a fast iteration loop.
Yes. Prototype in the RunComfy AI Playground Web UI to settle on your image, prompt, resolution, and duration, then call the same model through the RunComfy API with identical parameters. This lets you keep Minimax H3 Image to Video settings consistent between manual exploration and batch or scheduled jobs in your own application.
Generations consume usd or credits from your RunComfy balance. The rate is $0.09 per second at 768p and $0.145 per second at 2K. A 5-second clip therefore costs $0.45 at 768p or $0.725 at 2K; 10 seconds costs $0.90 or $1.45; 15 seconds costs $1.35 or $2.175. New users typically receive a free trial amount to test with; for billing questions, contact hi@runcomfy.com.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
