MiniMax H3 Lite Reference-to-Video

minimax/h3-lite/reference-to-video

Generate videos with native audio, 4–15 second durations, and 480p or 768p resolution.

Examples

MiniMax H3 Lite Reference-to-Video Examples 1

Parameters

NameTypeDefaultConstraintsDescription
prompt *Prompttextarea—≤ 5000 charsText description of the desired video scene and interactions.
reference_imagesReference Imagesimage_upload—image/* · 0–9 itemsUp 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 Audiosvideo_upload_group—audio/* · 0–3 itemsUp 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 Ratioselect16:921:9 | 16:9 | 4:3 | 1:1 | 3:4 | 9:16Output aspect ratio.
resolutionResolutionselect768p768p | 480pOutput video resolution.
durationDurationselect54 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | …Output video duration in seconds.

Output fields

FieldTypeDescription
videosarray<string>Generated video URLs with native audio.

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-lite/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-lite/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-lite/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 Lite Reference-to-Video

Generate videos with native audio, 4–15 second durations, and 480p or 768p resolution.

Inputs

ParameterRequiredType / limits / default
promptYesstring; 1–5000 characters. Text description of the desired video scene and interactions.
reference_imagesNoarray; max 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_videosNoarray; max 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_audiosNoarray; max 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_ratioNostring; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; default: 16:9. Output aspect ratio.
resolutionNostring; 768p, 480p; default: 768p. Output video resolution.
durationNointeger; 4–15; 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15; default: 5. Output video duration in seconds.

Prompt must be non-empty. This endpoint accepts up to 5000 characters to match the current MaaS input contract (WaveSpeed supports up to 7000).

Provide at least one reference image or video; audio cannot be the only input. Images: 256–5760 pixels per side, aspect ratio 0.4–2.5. Videos: MP4/MOV, at most 50 MB each, 23.976–60 FPS, 256–5760 pixels per side, aspect ratio 0.4–2.5. Reference audio: WAV/MP3, at most 15 MB each, 2–15 seconds per clip and at most 15 seconds combined; audio is not automatically trimmed.

Listing price

ResolutionUSD / secondCredits / second
480p$0.0252.5
768p$0.044

Account discounts are applied separately. 1 USD = 100 credits. Generated audio has no extra charge.

Current charge = rate × (output seconds + ceil(min(sum(max(each reference-video seconds, 2)), 15))) + $0.02 × max(reference image count − 5, 0). First 5 reference images and reference audio are free.

API example

Replace example URLs with uploaded media. Submit once, then poll task_uuid until completed or failed. Successful output.videos is an array of video URLs. Image and last_image accept one-element arrays; Nami forwards each as a single upstream URL.

POST https://www.namifusion.com/api/v1/marketplace/run/minimax/h3-lite/reference-to-video
Authorization: Bearer YOUR_NAMIFUSION_API_KEY
Content-Type: application/json

{
  "input": {
    "prompt": "Colorful shapes move gently through the scene.",
    "duration": 5,
    "resolution": "768p",
    "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

WaveSpeed

Related models

xAI Grok Imagine Video v1.5 Reference to Video
Reference to VideoX Ai

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.

from $0.850 / per run
Vidu Q4 Preview Reference to Video
Reference to VideoVidu

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.

from $0.475 / per run
MiniMax H3 Reference to Video
Reference to VideoMinimax

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.

from $0.650 / per run
MiniMax H3 Singularity Reference-to-Video LoRA
Reference to VideoMinimax H3 Singularity

MiniMax H3 Singularity Reference-to-Video LoRA

Generate videos with native stereo audio, 3–15 second durations and four resolution tiers. Supports custom LoRAs.

from $0.300 / per run
MiniMax H3 Singularity Reference-to-Video
Reference to VideoMinimax H3 Singularity

MiniMax H3 Singularity Reference-to-Video

Generate videos with native stereo audio, 3–15 second durations and four resolution tiers.

from $0.250 / per run
Kling 4.0 Reference to Video
Reference to VideoKling

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.

from $0.785 / per run
Gemini Omni Flash Reference to Video API
Reference to VideoGoogle

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.

from $1.28 / per run
Seedance 2.0 Mini Reference to Video
Reference to VideoDoubao

Seedance 2.0 Mini Reference to Video

Seedance 2.0 Mini Reference-to-Video is a high-speed, cost-effective video generation model developed by ByteDance, engineered specifically for creating multi-shot videos with a cinematic feel. By seamlessly combining reference images with text prompts, it generates highly narrative video segments. The model features advanced AI camera control and ensures robust character consistency across different scenes. It supports multiple output resolutions from 480P up to 4K, durations ranging from 4 to 15 seconds, and flexible aspect ratios. Complete with an out-of-the-box REST inference API, it delivers exceptional performance with zero cold starts, offering an affordable yet premium solution for professional video creation.

from $0.3591 / per run