MiniMax H3 Highspeed Reference-to-Video
minimax/h3-highspeed/reference-to-video
Generate 4–15 second videos at 768p.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | Text description of the desired video scene and interactions. |
| reference_imagesReference Images | image_upload | — | image/* · 0–9 items | Up to 9 reference image URLs. At least one reference image or video is required. Images must be 256-5760 pixels per side, with a width-to-height ratio of 0.4-2.5. |
| reference_audiosReference Audios | audio_upload_group | — | audio/* · 0–3 items | Up to 3 optional WAV or MP3 reference audio URLs, up to 15 MB per file. Each clip must be 2-15 seconds, with a combined maximum of 15 seconds. Audio is not automatically trimmed and cannot be provided alone. |
| aspect_ratioAspect Ratio | select | 16:9 | 21:9 | 16:9 | 4:3 | 1:1 | 3:4 | 9:16 | Output aspect ratio. |
| resolutionResolution | select | 768p | 768p | Output video resolution. |
| durationDuration | select | 5 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | … | Output video duration in seconds. |
Output fields
| Field | Type | Description |
|---|---|---|
| videos | array<string> | Generated video URLs. |
API
Call this model through one unified REST API. Get a key on the API Keys page.
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/minimax/h3-highspeed/reference-to-video" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
"aspect_ratio": "16:9",
"resolution": "768p",
"duration": 5
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/minimax/h3-highspeed/reference-to-video",
headers=HEADERS,
json={
"input": {
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
"aspect_ratio": "16:9",
"resolution": "768p",
"duration": 5
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 1800s server-side.
deadline = time.time() + 1860
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/minimax/h3-highspeed/reference-to-video", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
"aspect_ratio": "16:9",
"resolution": "768p",
"duration": 5
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 1800s server-side.
const deadline = Date.now() + 1860 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);Documentation
MiniMax H3 Highspeed Reference-to-Video
Generate 4–15 second videos at 768p.
Inputs
| Parameter | Required | Type / allowed values / default |
|---|---|---|
prompt | Required | string; max 5000 characters. Text description of the desired video scene and interactions. |
reference_images | Optional | array; max count: 9. Up to 9 reference image URLs. At least one reference image or video is required. Images must be 256-5760 pixels per side, with a width-to-height ratio of 0.4-2.5. |
reference_videos | Optional | array; max count: 3. Up to 3 reference video URLs. Clips are adjusted to 2-15 seconds each, with a combined maximum of 15 seconds; longer clips are trimmed and shorter clips are extended. Use MP4 or MOV, up to 50 MB per file, 256-5760 pixels per side, width-to-height ratio 0.4-2.5, and 23.976-60 FPS. At least one image or video is required. |
reference_audios | Optional | array; max count: 3. Up to 3 optional WAV or MP3 reference audio URLs, up to 15 MB per file. Each clip must be 2-15 seconds, with a combined maximum of 15 seconds. Audio is not automatically trimmed and cannot be provided alone. |
aspect_ratio | Optional | string; 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16; default: "16:9". Output aspect ratio. |
resolution | Optional | string; 768p; default: "768p". Output video resolution. |
duration | Optional | integer; 4 / 5 / 6 / 7 / 8 / 9 / 10 / 11 / 12 / 13 / 14 / 15; default: 5. Output video duration in seconds. |
Nami accepts up to 5000 prompt characters to match the current MaaS contract. Required prompts must be non-empty.
Provide at least one reference image or video; audio alone is not supported. Up to 9 images, 3 videos and 3 audio clips. Images/video frames: 256–5760 pixels per side, aspect ratio 0.4–2.5. MP4/MOV videos: up to 50 MB each, 23.976–60 FPS. Video references are adjusted to 2–15 seconds each and 15 seconds combined. WAV/MP3 reference audio: up to 15 MB each, 2–15 seconds per clip, 15 seconds combined; audio is not automatically trimmed.
Listing price
1 USD = 100 credits. Account discounts are applied separately.
768p: $0.06 per output second (6 credits). Output duration: 4–15 whole seconds; default 5.
Reference charge: $0.06 × ceil(min(sum(max(each reference-video duration, 2)), 15)). First 5 reference images are free; each additional image costs $0.03 (3 credits). Reference audio is free.
API usage
Use reachable media URLs. Submit once, then poll task_uuid until completed or failed; successful output.videos contains the video URLs.
POST https://www.namifusion.com/api/v1/marketplace/run/minimax/h3-highspeed/reference-to-video
Authorization: Bearer YOUR_NAMIFUSION_API_KEY
Content-Type: application/json
{
"input": {
"resolution": "768p",
"prompt": "A colorful scene with gentle natural movement.",
"duration": 5,
"reference_images": [
"https://example.com/subject.png"
],
"aspect_ratio": "16:9"
}
}
GET https://www.namifusion.com/api/v1/marketplace/run/tasks/{task_uuid}
Authorization: Bearer YOUR_NAMIFUSION_API_KEY
Related models
xAI Grok Imagine Video v1.5 Reference to Video
Generate a 1-15 second video from a prompt and 1-7 reference images at 480p or 720p.
Vidu Q4 Preview Reference to Video
Generate a 3–16 second video from a prompt with optional references: up to 15 images and 3 audio clips. Supports aspect ratio selection, audio generation and 540p–4k resolution.
MiniMax H3 Reference to Video
MiniMax H3 Reference to Video generates coherent 2K videos from natural-language prompts and multimodal references, including images, videos, and audio, guiding subject consistency, motion, timing, visual style, and scene continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
MiniMax H3 Lite Reference-to-Video
Generate videos with native audio, 4–15 second durations, and 480p or 768p resolution.
MiniMax H3 Singularity Reference-to-Video LoRA
Generate videos with native stereo audio, 3–15 second durations and four resolution tiers. Supports custom LoRAs.
MiniMax H3 Singularity Reference-to-Video
Generate videos with native stereo audio, 3–15 second durations and four resolution tiers.
Kling 4.0 Reference to Video
Generate 3–30 second videos using image, video and audio references, with native prompt references and 720p or 1080p output.
Gemini Omni Flash Reference to Video API
Gemini Omni Flash Reference to Video creates short AI videos with synchronized audio from one or more reference images and a text prompt, preserving visual identity and following the provided references for guided multimodal video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.