Alla modellervideoMiniMax H3 Max Image-to-Video

MiniMax H3 Max Image-to-Video

av MiniMax

Testa på Kunya
video

MiniMax H3 Max Image-to-Video

Hailuo H3 Max — fast first/last-frame image-to-video at 480P/768P (5–15s)

Modell-ID:minimax-h3-max-i2v

API-dokumentation

Generate video with this model.

POST/api/v1/videos/generations
GET /api/v1/videos/generations
Request body
{
  "model": "minimax-h3-max-i2v",
  "prompt": "A cinematic drone shot over a coastal city at sunset",
  "duration": 5,
  "resolution": "768p",
  "aspect_ratio": "16:9",
  "image_url": "https://example.com/start-frame.jpg",
  "end_image_url": "https://example.com/end-frame.jpg"
}
cURL-exempel
curl -X POST https://kunya.ai/api/v1/videos/generations \
  -H "Authorization: Bearer kunya_YOUR_API_KEY" \
  -H "Content-Type: application/json"
  -d '{"model":"minimax-h3-max-i2v","prompt":"A cinematic drone shot over a coastal city at sunset","duration":5,"resolution":"768p","aspect_ratio":"16:9","image_url":"https://example.com/start-frame.jpg","end_image_url":"https://example.com/end-frame.jpg"}'

Anteckningar

  • •Video generation is asynchronous — poll `GET /api/v1/videos/status?task_id=...` until complete.
  • •Supported resolutions: 480p, 768p.
  • •MiniMax H3 uses the V2 API — resolution: "768p" (768P, $0.08/s) or "1080p" (2K, $0.13/s), 4–15s, native audio.
  • •I2V: image_url required; aspect ratio is adaptive from the input image.
  • •Max duration: 15s (may vary by resolution).

Priser

Kostnad$0.104 per sekund

Funktioner

Streaming Nej
Vision Nej
Resonemang Nej
Verktyg Nej
LeverantörMiniMax
Testa på Kunya

Liknande modeller

Hailuo 2.3

MiniMax

Latest MiniMax model — cinematic motion, expressive faces, anime & illustration styles, 15 camera commands

API-dokumentation

MiniMax H3 Reference-to-Video

MiniMax

Hailuo H3 — reference images, video, and audio for character/scene-consistent 2K video (4–15s)

API-dokumentation

Kling Motion Brush

FAL AI (Kling)

Kling face puppeteering - drive faces with your video

API-dokumentation

Kling O3 4K Ref2V (FAL)

FAL AI (Kling 4K)

Kling O3 4K — reference-to-video with @Element character locking at native 4K. Up to 7 refs (3-15s)

API-dokumentation