fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

minimax/h3-max/image-to-video

Learn more about H3 Max

Released Aug 27, 2026

Inference

Commercial use

Schema

Playground API Examples

SandboxOpen in Sandbox Try free

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

minimax/h3-max/image-to-video

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

{ "video": { "url": "https://v3b.fal.media/files/b/0aa7ec74/bNpa9-5B0ZKqsrGfdqxZt_minimax-h3.mp4", "content_type": "video/mp4", "file_name": "bNpa9-5B0ZKqsrGfdqxZt_minimax-h3.mp4", "file_size": 3601950 }, "expanded_prompt": "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.\n\nintegrated_multimodal_description: [Shot 1] Cinematic, live-action, close-up. The scene opens with <Picture 1>, featuring a young woman (S1) with pale skin, dark hair with loose strands framing her face, and large, thin-rimmed silver glasses. She is wearing a black ribbed long-sleeve shirt with a low neckline and a silver chain necklace adorned with small cross charms. She is seated in a grey fabric armchair, positioned near a window with light beige curtains that allow soft, diffused daylight to illuminate the left side of her face. Initially, S1 is looking downward with a thoughtful, slightly perplexed expression. The camera is a Static Shot. At 00:01.000, she slowly lifts her head and shifts her gaze toward the camera, her eyes widening slightly as she becomes curious. Her lips part, and she speaks with a soft, breathy, and slightly hesitant tone: <d>[English] I heard something. MiniMax H3 Max is here?.. Is that true?</d> As she speaks, her eyebrows knit together in a questioning manner, and her head tilts slightly to the right. Her facial movements are subtle and natural, with her lips syncing perfectly to the dialogue. By 00:05.000, she maintains a look of hopeful anticipation and slight uncertainty as the shot ends.\n\noverall_soundscape: The environment is characterized by a quiet, indoor room tone with the faint, distant hum of city traffic filtering through the window. The primary sound is the clear, close-mic recording of S1's voice, featuring the soft intake of breath before she speaks and the subtle moisture of her lip movements.\n\nnon_diegetic_music: N/A", "timings": { "inference": 2.7652357418555766 } }