Gemini Omni Flash Reference to Video API
google/gemini-omni-flash/reference-to-video
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.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| images *Images | image_upload | — | video/* · 1–4 items | Reference image URLs to incorporate into the video. |
| prompt *Prompt | textarea | — | ≤ 5000 chars | Text prompt describing the video. You can refer to images with tags like <IMAGE_REF_0>. |
| aspect_ratioAspect Ratio | select | 16:9 | 16:9 | 9:16 | Aspect ratio of the generated video. |
| durationDuration | select | 8 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | Duration of the generated video in seconds. |
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/google/gemini-omni-flash/reference-to-video" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"images": "https://example.com/input.jpg",
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
"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://example.com/input.jpg",
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
"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://example.com/input.jpg",
"prompt": "A cinematic portrait, dramatic rim light, shallow depth of field",
"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);Documentation
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
16:9for landscape output and9:16for portrait-first content. - No cold starts, production-friendly: Optimized for responsive generation and predictable cost in testing and scaled usage.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model Name | Gemini Omni Flash Reference to Video API |
| Model ID | google/gemini-omni-flash/reference-to-video |
| Task Type | Image-to-video |
| Model Architecture | Reference-guided multimodal video generation model |
| Input | One or more reference image URLs + Prompt |
| Output | Video with synchronized audio |
| Supported Aspect Ratio | 16:9, 9:16 |
| Default Aspect Ratio | 16:9 |
| Duration Range | 3–10 seconds |
| Default Duration | 8 seconds |
| Audio Capability | Yes, synchronized audio generation |
| Prompt Control | Scene, motion, camera behavior, pacing, and audio direction |
| Reference Tagging | Supports tags such as <IMAGE_REF_0> inside the Prompt |
| Latency Profile | No cold starts; suitable for responsive online generation |
| Output Format | Short-form video clip |
Sample Prompts
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.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.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
| Item | Price |
|---|---|
| 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.
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.
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.
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.
Seedance 2.5 Reference to Video
The "Reference-to-Video" feature of Seedance 2.5 is the ultimate solution for visual stylistic unity. It precisely extracts artistic styles, lighting tones, or compositional intents from reference materials and seamlessly integrates them into newly generated videos, ensuring a highly consistent visual language for your creative series.
Seedance 2.0 Fast reference-to-video
Seedance 2.0 Fast (Video-Edit) edits an input video from a natural-language prompt at a faster, cheaper tier. Built on ByteDance Seed's unified multimodal architecture, it preserves subject identity, composition, and motion while rewriting lighting, style, weather, environment, or specific elements as instructed. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.