MiniMax Available on Video Blade

MiniMax H3 Image to Video API

Image to video

MiniMax H3 (Hailuo 03) turns one image, or a first and last frame pair, into a clip of up to 15 seconds at 768p or 2K, with stereo sound.

8-second clip from · per second
Live price in USD — you see the exact price before anything runs. Plans start at .
Use from your AI agent Get started
InputInput image 1↑ Result above
Example output · first 10 seconds
A still of a woman on a rainy evening platform comes to life as the train doors close behind her.
“Animate the source image into a 12-second restrained cinematic scene. Preserve the woman’s face, chin-length dark hair, dark green wool coat, cream scarf, brown shoulder bag, transparent umbrella, train design, platform layout, and evening color palette. [0–3 seconds] Begin almost still. Rain falls steadily, water moves along the platform edge, and warm reflections shimmer subtly. The woman breathes naturally and shifts her gaze slightly toward the train. [3–7 seconds] The train doors close behind her and the interior lights brighten for a moment. A soft gust moves her scarf and a few strands of hair. She tightens her grip on the umbrella without opening it. Keep the performance understated and realistic. [7–10 seconds] The train starts moving slowly. Track sideways with the woman while the lit windows pass behind her, creating gentle parallax and moving reflections across her face and coat. [10–12 seconds] After the train clears the platform, she takes one small step forward and looks down the now-empty track. End on a quiet medium shot with rain continuing and distant red signal lights softly out of focus. Audio: natural rain, low train motor, closing-door chime without spoken announcements, wheels beginning to move, soft fabric movement, and subdued station ambience. No dialogue, subtitles, dramatic crying, umbrella opening, identity change, wardrobe change, extra characters entering the foreground, distorted train geometry, rapid camera movement, or exaggerated wind.”

What MiniMax H3 Image to Video is good for

MiniMax H3, also called Hailuo 03, is MiniMax's general-purpose video model, and this mode works from pictures you already have. Give it one image as the opening state, or a first and a last frame to set how the shot begins and ends; it adds character motion, camera moves, and stereo sound while keeping the details you tell it to preserve. It suits animated posters, product spotlights, and UI demos.

  • Animated posters and key art with subtle motion and ambient sound
  • Product spots that move from a hero shot to a detail close-up
  • UI and app demos where on-screen text must stay readable
  • Before-and-after transitions defined by a first and a last frame
  • Character portraits that start to breathe, glance, and react

MiniMax H3 Image to Video pricing

OptionPrice, USDVideo Blade tokens
Image to video · 768p tokens
Image to video · 2K tokens

Prices are per second and live from our price list. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing.

Use MiniMax H3 Image to Video from your AI agent

  1. Create an account on Video Blade and pick a plan — from .
  2. Copy the agent link from your dashboard into Claude Code, Codex or Cursor.
  3. Give the agent the start frame — a file path or a link — and say the phrase below: it shows the price, runs MiniMax H3 Image to Video and saves the result.
Tell your agent

Turn my bakery storefront photo into a 10-second 2K clip with MiniMax H3: the neon sign flickers on at dusk, rain streaks the window, soft street sounds.

This request ≈ · Image to video · 2K · 10 s

MiniMax H3 Image to Video FAQ

How much does MiniMax H3 Image to Video cost?

8-second clip from · per second. Prices are live from our price list, and you see the exact price before anything runs.

Should I use one image or first and last frames with MiniMax H3 Image to Video?

One image sets the opening look, and your prompt guides where the motion goes from there; it works well for natural character movement, scenery, and camera moves. A first and last frame pair also locks in where the shot ends, which suits product reveals, before-and-after shots, and planned transitions.

Can MiniMax H3 Image to Video add sound to an animated image?

Yes. MiniMax H3 produces stereo audio in the same pass as the video, so a still can come back with dialogue, music, room ambience, or sound effects that match the movement. Describe the sound in the prompt alongside the motion and camera direction.

How do I use MiniMax H3 Image to Video from my AI agent?

Create a Video Blade account, paste the agent link from your dashboard into Claude Code, Codex or Cursor, and ask: “Turn my bakery storefront photo into a 10-second 2K clip with MiniMax H3: the neon sign flickers on at dusk, rain streaks the window, soft street sounds.” The agent runs MiniMax H3 Image to Video (model id minimax-h3-image-to-video), shows the price before it starts and saves the result to your dashboard.

How is MiniMax H3 Image to Video billed?

By the second of video: the rate depends on the option you pick (mode, resolution, sound), and a clip costs the rate times its length. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing. Current prices are shown on this page.

What settings does MiniMax H3 Image to Video support?

Length: 4 s, 5 s, 6 s, 7 s, 8 s, 9 s, 10 s, 11 s, 12 s, 13 s, 14 s or 15 s. Resolution: 768p or 2K.

MiniMax H3 Image to Video in the Video Blade API
minimax-h3-image-to-video

Your agent sends this model id with the order; the result lands in the project, and every request is in your generation log with its price.

Through Video Blade a clip is ordered from a prompt with an optional start frame (and an end frame where the model takes one), in the lengths and resolutions the model offers.

POST /api/v1/projects/{id}/video-sessions/{item_id}/generate
{"prompt": "…", "model": "minimax-h3-image-to-video", "duration": …, "start_url": "https://…"}
Parameters and API reference →Getting started →

Similar models

Kling 3.0 Omni Image to Video example output Coming soon
Kuaishou

Kling 3.0 Omni Image to Video

8-second clip from · per second
Seedance 2.0 example output
ByteDance

Seedance 2.0

Text to videoImage to video 8-second clip from · per second
Seedance 2.5 example output
ByteDance

Seedance 2.5

Text to videoImage to video 8-second clip from · per second
Wan 3.0 Video example output
Alibaba

Wan 3.0 Video

Text to videoImage to video 8-second clip from · per second

Compare all video models by price →