Veo3.1 Reference-to-Video API by Google
Create richly detailed videos guided by visual references. Veo 3.1 Reference-to-Video preserves characters, style, and composition across scenes for consistent, visually coherent storytelling.
Invoer
Uitvoer
InactiefElke uitvoering kost $0.2. Voor $10 kunt u ongeveer 50 keer uitvoeren.
U kunt doorgaan met:
Codevoorbeeld
import requests
import time
# Step 1: Start video generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "google/veo3.1/reference-to-video",
"prompt": "A beautiful sunset over the ocean with gentle waves",
"width": 512,
"height": 512,
"duration": 3,
"fps": 24,
}
generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]
# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
def check_status():
while True:
response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
result = response.json()
if result["data"]["status"] in ["completed", "succeeded"]:
print("Generated video:", result["data"]["outputs"][0])
return result["data"]["outputs"][0]
elif result["data"]["status"] == "failed":
raise Exception(result["data"]["error"] or "Generation failed")
else:
# Still processing, wait 2 seconds
time.sleep(2)
video_url = check_status()Installeren
Installeer het vereiste pakket voor uw programmeertaal.
pip install requestsAuthenticatie
Alle API-verzoeken vereisen authenticatie via een API-sleutel. U kunt uw API-sleutel ophalen via het Atlas Cloud dashboard.
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP-headers
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Stel uw API-sleutel nooit bloot in client-side code of openbare repositories. Gebruik in plaats daarvan omgevingsvariabelen of een backend-proxy.
Een verzoek indienen
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "your-model",
"prompt": "A beautiful landscape"
}
response = requests.post(url, headers=headers, json=data)
print(response.json())Een verzoek indienen
Dien een asynchroon generatieverzoek in. De API retourneert een voorspellings-ID waarmee u de status kunt controleren en het resultaat kunt ophalen.
/api/v1/model/generateVideoVerzoekinhoud
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "google/veo3.1/reference-to-video",
"input": {
"prompt": "A beautiful sunset over the ocean with gentle waves"
}
}
response = requests.post(url, headers=headers, json=data)
result = response.json()
print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")Antwoord
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Status controleren
Bevraag het voorspellings-eindpunt om de huidige status van uw verzoek te controleren.
/api/v1/model/prediction/{prediction_id}Polling-voorbeeld
import requests
import time
prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
while True:
response = requests.get(url, headers=headers)
result = response.json()
status = result["data"]["status"]
print(f"Status: {status}")
if status in ["completed", "succeeded"]:
output_url = result["data"]["outputs"][0]
print(f"Output URL: {output_url}")
break
elif status == "failed":
print(f"Error: {result['data'].get('error', 'Unknown')}")
break
time.sleep(3)Statuswaarden
processingHet verzoek wordt nog verwerkt.completedDe generatie is voltooid. Resultaten zijn beschikbaar.succeededDe generatie is geslaagd. Resultaten zijn beschikbaar.failedDe generatie is mislukt. Controleer het foutveld.Voltooid antwoord
{
"data": {
"id": "pred_abc123",
"status": "completed",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.mp4"
],
"metrics": {
"predict_time": 45.2
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}
}Bestanden uploaden
Upload bestanden naar Atlas Cloud opslag en ontvang een URL die u kunt gebruiken in uw API-verzoeken. Gebruik multipart/form-data om te uploaden.
/api/v1/model/uploadMediaUpload-voorbeeld
import requests
url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
with open("image.png", "rb") as f:
files = {"file": ("image.png", f, "image/png")}
response = requests.post(url, headers=headers, files=files)
result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")Antwoord
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Invoer-Schema
De volgende parameters worden geaccepteerd in de verzoekinhoud.
Geen parameters beschikbaar.
Voorbeeld verzoekinhoud
{
"model": "google/veo3.1/reference-to-video"
}Uitvoer-Schema
De API retourneert een voorspellingsantwoord met de gegenereerde uitvoer-URL's.
Voorbeeldantwoord
{
"id": "pred_abc123",
"status": "completed",
"model": "model-name",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.mp4"
],
"metrics": {
"predict_time": 45.2
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}Atlas Cloud Skills
Atlas Cloud Skills integreert meer dan 300 AI-modellen rechtstreeks in uw AI-codeerassistent. Eén commando om te installeren, gebruik daarna natuurlijke taal om afbeeldingen, video's te genereren en te chatten met LLMs.
Ondersteunde clients
Installeren
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI-sleutel instellen
Haal uw API-sleutel op via het Atlas Cloud dashboard en stel deze in als omgevingsvariabele.
export ATLASCLOUD_API_KEY="your-api-key-here"Mogelijkheden
Eenmaal geïnstalleerd kunt u natuurlijke taal gebruiken in uw AI-assistent om toegang te krijgen tot alle Atlas Cloud modellen.
MCP-server
De Atlas Cloud MCP-server verbindt uw IDE met meer dan 300 AI-modellen via het Model Context Protocol. Werkt met elke MCP-compatibele client.
Ondersteunde clients
Installeren
npx -y atlascloud-mcpConfiguratie
Voeg de volgende configuratie toe aan het MCP-instellingenbestand van uw IDE.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Beschikbare tools
API Schema
Schema niet beschikbaarInloggen om aanvraaggeschiedenis te bekijken
U moet ingelogd zijn om toegang te krijgen tot uw modelaanvraaggeschiedenis.
InloggenGoogle Veo 3.1 — Reference-to-Video Model
Veo 3.1 Reference-to-Video brings static images to life by combining visual reference consistency with cinematic motion generation. Powered by Google DeepMind’s next-generation Veo 3.1 architecture, this model transforms up to three reference images into coherent 5-second videos with smooth motion, accurate visual alignment, and synchronized native audio.
🌟 Key Features
🧠 Multi-Image Reference Support
- Accepts up to three reference images to define the subject, environment, or style.
- Maintains consistent identity, lighting, and appearance across frames.
- Ideal for animating people, objects, or scenes with reliable fidelity.
🎬 Cinematic Video Generation
- Produces 5-second motion clips at 1080p or 720p resolution.
- Adds camera dynamics such as panning, zooming, or subtle perspective drift.
- Supports synchronized audio generation, matching dialogue or ambient context.
💡 Smart Prompt Adherence
- Interprets both text instructions and visual cues for precise motion storytelling.
- Automatically harmonizes character interactions, props, and backgrounds.
⚙️ Capabilities
-
Input:
- Up to 3 reference images (JPEG / PNG / WEBP)
- Text prompt describing motion, action, and scene context
-
Output:
- 8-second MP4 video (720p or 1080p)
- Optional synchronized audio
-
Negative Prompt (optional):
- Exclude unwanted artifacts or elements (e.g., “no text”, “no flicker”).
-
Seed (optional):
- Reproduce specific results for consistent creative control.
💰 Pricing
| Duration | Resolution | With Audio | Without Audio |
|---|---|---|---|
| 8 seconds | 720p | $3.20 | $1.60 |
| 8 seconds | 1080p | $3.20 | $1.60 |
✅ Commercial use allowed
🧩 How to Use
- Upload up to 3 reference images — define the subject, object, or visual style.
- Write a text prompt — describe the action, setting, and camera motion.
- (Optional) Add a negative prompt to remove unwanted details.
- Choose resolution (720p or 1080p).
- (Optional) Enable audio generation for synchronized sound.
- Click Run to generate your 5-second cinematic video.
💡 Best Practices
- Use clear, well-lit reference images with similar styles and proportions.
- Keep prompts concise but specific (e.g., “The man in image 1 waves to the penguins in image 2 under bright sunlight”).
- Avoid overly complex scenarios with many characters or fast movement.
- Enable audio for more immersive storytelling results.
📝 Notes
- Ensure uploaded images are valid and accessible URLs or uploaded locally.
- If the output looks unstable, reduce reference count or simplify the prompt.
- Follow Google’s content safety rules; modify the prompt if flagged.
- For best performance, prefer portrait-oriented subjects and balanced lighting.
