Gemini Omni Flash Reference to Video API

google/gemini-omni-flash/reference-to-video

google/gemini-omni-flash/reference-to-video. Görsel, video ve yüz değiştirme model API’lerine göz at. Bir modeli dene ve birleşik REST API ile entegre et.

İlgili modeller

Gemini Omni Flash Reference to Video API İlgili modeller 1

Tüm parametreler, çıktı şeması ve güncel fiyatlar

Yapay zeka model API pazarıTek platformda her şeyEn popülerKoşullarGörsel, video ve yüz değiştirme model API’lerine göz at. Bir modeli dene ve birleşik REST API ile entegre et.
images *Imagesimage_upload—video/* · 1–4 items
prompt *Prompttextarea—≤ 5000 chars
aspect_ratioAspect Ratioselect16:916:9 | 9:16
durationDurationselect83 | 4 | 5 | 6 | 7 | 8 | 9 | 10

Tüm parametreler, çıktı şeması ve güncel fiyatlar

Daha fazla bilgiTek platformda her şeyGörsel, video ve yüz değiştirme model API’lerine göz at. Bir modeli dene ve birleşik REST API ile entegre et.
videosarray<string>

API

Görsel, video ve yüz değiştirme model API’lerine göz at. Bir modeli dene ve birleşik REST API ile entegre et.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/google/gemini-omni-flash/reference-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "images": [
      "https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
    ],
    "prompt": "Keep the reference subject consistent while creating a cinematic walking scene with natural motion and coherent lighting.",
    "aspect_ratio": "16:9",
    "duration": 8
  }
}'

# 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/google/gemini-omni-flash/reference-to-video",
    headers=HEADERS,
    json={
        "input": {
            "images": [
                "https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
            ],
            "prompt": "Keep the reference subject consistent while creating a cinematic walking scene with natural motion and coherent lighting.",
            "aspect_ratio": "16:9",
            "duration": 8
        }
    },
)
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 300s server-side.
deadline = time.time() + 360
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/google/gemini-omni-flash/reference-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "images": [
        "https://assets-public.namifusion.com/marketplace/images/2026-06-12/638e1ee18ac7.jpeg"
      ],
      "prompt": "Keep the reference subject consistent while creating a cinematic walking scene with natural motion and coherent lighting.",
      "aspect_ratio": "16:9",
      "duration": 8
    }
  }),
});
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 300s server-side.
const deadline = Date.now() + 360 * 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);

API belgeleri

Gemini Omni Flash Reference to Video API

Create short, reference-guided videos with synchronized audio—fast, consistent, and cost-efficient.

Gemini Omni Flash Reference to Video is an image-to-video model that generates short videos with synchronized audio from one or more reference images plus a text prompt. It is designed for workflows that require stronger subject, style, or layout consistency, while also offering no cold starts, reliable performance, and affordable pricing.

🚀 Key Features

  • Reference-guided video generation: Use one or more reference images to steer subject appearance, style, composition, and overall visual direction.
  • Stronger visual consistency: Well suited for preserving character identity, product appearance, object details, or brand-aligned visuals across generated clips.
  • Synchronized audio output: Generates audio together with the video, enabling more complete short-form content creation.
  • Prompt-driven motion and pacing: Control scene development, subject behavior, camera movement, pacing, and audio direction through natural language.
  • Simple aspect ratio control: Supports 16:9 for landscape output and 9:16 for portrait-first content.
  • No cold starts, production-friendly: Optimized for responsive generation and predictable cost in testing and scaled usage.

🛠️ Technical Specifications

ItemDetails
Model NameGemini Omni Flash Reference to Video API
Model IDgoogle/gemini-omni-flash/reference-to-video
Task TypeImage-to-video
Model ArchitectureReference-guided multimodal video generation model
InputOne or more reference image URLs + Prompt
OutputVideo with synchronized audio
Supported Aspect Ratio16:9, 9:16
Default Aspect Ratio16:9
Duration Range3–10 seconds
Default Duration8 seconds
Audio CapabilityYes, synchronized audio generation
Prompt ControlScene, motion, camera behavior, pacing, and audio direction
Reference TaggingSupports tags such as <IMAGE_REF_0> inside the Prompt
Latency ProfileNo cold starts; suitable for responsive online generation
Output FormatShort-form video clip

Sample Prompts

  1. The character in <IMAGE_REF_0> walks through a neon-lit street at night, slow forward camera push, subtle fabric movement in the wind, cinematic pacing, with ambient city audio.
  2. Using <IMAGE_REF_0> and <IMAGE_REF_1> as references, create a product showcase video in a clean studio setting, slow rotation of the subject, gentle orbit camera movement, with minimal futuristic sound design.
  3. Follow the visual style of <IMAGE_REF_0> and generate a vertical video where the subject turns, smiles, and waves to the camera, with soft background blur, upbeat pacing, and natural environmental audio.

💰 Pricing

ItemPrice
Base Price$0.16 / second
3s video$0.48
5s video$0.80
8s video$1.28
10s video$1.60

💡 Best Use Cases

  • E-commerce and product marketing: Turn product images into short promotional videos with audio for ads, landing pages, and social campaigns.
  • Character and IP content: Maintain visual identity for people, mascots, or virtual characters across short generated clips.
  • Social media short-form production: Create both landscape and portrait videos optimized for different publishing channels.
  • Creative prototyping and previsualization: Test motion ideas, scene direction, and audiovisual concepts before full production.

🔗 Related Models

  • Google Gemini Omni Flash Image To Video: A broader image-to-video option for more general generation workflows.
  • Google Gemini Omni Flash Text To Video: Best for prompt-only video generation when no reference images are required.