Log in
TechniqueBy HypernaturalVersion 4, updated

H3 Max: image to video

hn/h3-max-image-to-video

Animate a still with MiniMax H3 Max image-to-video (or its reference-to-video mode when characters or products need reference pictures): the fastest and cheapest video model, with good motion and performance but smoothed, painted-looking hair and skin up close. Use to draft every shot quickly, and for wide shots or subjects without fine texture; upgrade to kling-v3-image-to-video or seedance-2-5-image-to-video where close-up realism, 1080p grain or complex physics matter.

SKILL.md

Give it a first frame, a prompt, and optionally a last frame or reference pictures; get a clip back in a fraction of the time and price of Kling or Seedance, with good motion and acting. The cost is fine detail: facial hair, skin texture and hair strands come out mottled and smoothed together, painted rather than photographic, and close-ups look plastic. Draft on it, keep it for wide shots and subjects with little texture, and move to kling-v3-image-to-video (close-up texture) or seedance-2-5-image-to-video (physics, 1080p grain) where the shot needs it. For a still speaking an audio clip use h3-max-lipsync-a-still; for a scene with a dialogue track, h3-max-dialogue. Always H3 Max, never plain H3: Max is its fine-tune.

Inputs

  • The first frame. The output canvas follows its shape.
  • A last frame (optional), continuous with the first: derive it from the locked first frame (nano-banana-derive-last-frame). Two independently edited stills made her hair morph mid-shot.
  • Reference pictures (optional) for subjects the frame doesn't show well or who enter: up to 9 subjects and 9 pictures in all. Every subject keeps its first picture, the rest are dealt round-robin. Single views from a character sheet, not the sheet.

Run it

Call describe on the model before the first run in a job. Before that first run, a test included, show the person the still that will move and ask (core skill: the person decides every look).

run("fal/minimax/h3-max/image-to-video", {
  "image_url": "<job>/stills/shot04_first_c.png",
  "prompt": "<H3 prompt, see below>",
  "duration": 3.2,
  "resolution": "768P",
  "prompt_expansion_mode": "disabled",
  "seed": 5000
}, into="<job>/video/raw", unit="shot04_h3", tag="shot04")
  • duration: the length you want, in seconds as a float, from about 1 s up to 15 s. The clip may come back a little longer than asked (ask for 1 s, get 1.2 to 1.4 s); trim it to the shot. H3 returns 24 fps. Shots longer than about 15 s aren't advisable on any video model: split the shot at a cut or a pause.
  • resolution: 480P, 768P or 1080P, uppercase P. 1080P is 768P plus latent refinement. Priced per second by tier whatever the shape: 480P $0.055/s, 768P $0.088/s, 1080P $0.176/s (list, October 2026). 768P holds up for soft looks such as clay and paper-cut scaled to 1080p with lanczos; 1080P where texture must hold.
  • prompt_expansion_mode: "disabled": required by the schema, and fal's "balanced" rewrite adds a soundtrack.
  • end_image_url pins the last frame. seed is optional; vary it for takes.
  • With reference pictures, call fal/minimax/h3-max/reference-to-video instead, with the same fields plus "reference_image_urls": [...], in the order of the prompt's <Picture N> labels. The first frame is still image_url. Each picture must be 256 to 2,048 px a side with an aspect between 0.4 and 2.5, or fal rejects the whole request (wide logos are the usual offender): pad with the edge colour, never crop.

Prompt

Load h3-prompt-format first: the image-to-video shape without references, the reference-to-video shape with them. For this mode:

  • Say "big, clear motion" in the direction and spell out counts ("blinks exactly once").
  • H3 pushes in by default; state "static shot, locked on the opening framing" when the frame must hold.
  • Never name a removed accessory, even to forbid it: "no pin or badge" grew a pin by 1 s. Describe the clean state instead ("a plain, unadorned knit, the same from the first frame to the last").
  • Ask for the shot's own length. If the clip still runs longer than the shot, ask for the action in real time, then a hold.

What you get

An MP4 at 24 fps, opening on the first frame, a little longer than the duration asked, with generated sound. Trim to the shot (ffmpeg-frame-exact-trim), keeping the raw render.

Tips and traps

  • Plastic skin on an otherwise good take: add grain in post (ffmpeg-grain-for-plastic-skin) before re-rendering on another model.
  • Not for complex physical motion (papers falling, cloth in wind), 1080p photographic realism, or close-ups where beard, skin or hair texture must hold.
  • A draft approves composition and timing, not motion. Re-judge the motion on the final model.
  • H3 sometimes reaches for a raised index finger however it's directed; take the least-bad take rather than looping.
  • Lock in words what must not change, first frame to last. Unlocked, H3 turned an overcast sky blue with cartoon clouds and lit up a building that should stay dark. "The sky stays exactly the same pale grey from the first frame to the last."
  • Stylized looks: open the prompt with the medium ("Handmade paper-cut stop-motion animation", "3D CG claymation") and close with "Slightly stepped, handmade stop-motion movement". Give big, counted motion ("pulses twice"); add "Static shot, locked on the opening framing" unless the camera moves.
  • Saturated wardrobe drifts brighter over a clip. It reads as stepping into warmer light; leave it unless it jumps.
  • A pull-out on a diorama-style set can show the set's open black top: scale that shot up about 2.5%, cropping from the bottom.

Check it

  • Frame 0 against the still (and the end against a pinned last frame): python-check-pinned-frames.
  • Close-up texture at 100% against the source, if the shot is a close-up.
  • Then put the takes to the person with review_choose, the original shot as original or the earlier round as previous.

Workflows that use this skill

FAQs

Animate a still with MiniMax H3 Max image-to-video (or its reference-to-video mode when characters or products need reference pictures): the fastest and cheapest video model, with good motion and performance but smoothed, painted-looking hair and skin up close. Use to draft every shot quickly, and for wide shots or subjects without fine texture; upgrade to kling-v3-image-to-video or seedance-2-5-image-to-video where close-up realism, 1080p grain or complex physics matter.

Install Hypernatural Desktop, a free Mac app, and connect it to Claude Code, Codex or Claude Desktop. Then describe the video you want and your agent finds the skill itself, or paste this page's link (https://hypernatural.ai/skill/hn/h3-max-image-to-video) and it installs hn/h3-max-image-to-video and follows it.

It runs MiniMax H3 Max. Hypernatural Desktop has every one of them built in, so there are no API keys to set up, though you can bring your own.

The skill is free. You only pay for the AI generations it runs, and your agent shows you the price of every batch before it spends anything. Editing, captions and titles run on your Mac at no cost.

Yes. Ask your agent to adjust it for your job, or to save its own version. You can publish your version under your own handle so anyone can install it.

Go make something cool.

Install the app, open your agent, describe the video. That's the whole onboarding.

Sticker HypernaturalSticker BannerSticker TVBoy