kwaivgi/kling-video-o3-std/reference-to-video

bild-till-video

Kling Omni Video O3 (Standard) Reference-to-Video generates creative videos using character, prop, or scene references. Supports up to 7 reference images and optional video input.

Inmatning

Laddar parameterkonfiguration...

Utmatning

Vilande

Dina genererade videor visas här

Konfigurera parametrar och klicka på Kör för att börja generera

Varje körning kostar 0.071. För $10 kan du köra cirka 140 gånger.

Du kan fortsätta med:

Videouppskalning Videoförlängning

Parametrar

Kodexempel
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": "kwaivgi/kling-video-o3-std/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()

Installera

Installera det nödvändiga paketet för ditt programmeringsspråk.

bash

pip install requests

Autentisering

Alla API-förfrågningar kräver autentisering via en API key. Du kan hämta din API key från Atlas Cloud-instrumentpanelen.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP Headers

python

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

Håll din API key säker

Exponera aldrig din API key i klientkod eller publika arkiv. Använd miljövariabler eller en backend-proxy istället.

Skicka en förfrågan

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())

Skicka en förfrågan

Skicka en asynkron genereringsförfrågan. API:et returnerar ett prediction ID som du kan använda för att kontrollera statusen och hämta resultatet.

POST/api/v1/model/generateVideo

Förfrågningsinnehåll

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "kwaivgi/kling-video-o3-std/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']}")

Svar

{
  "id": "pred_abc123",
  "status": "processing",
  "model": "model-name",
  "created_at": "2025-01-01T00:00:00Z"
}

Kontrollera status

Polla prediction-endpointen för att kontrollera den aktuella statusen för din förfrågan.

GET/api/v1/model/prediction/{prediction_id}

Polling-exempel

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)

Statusvärden

processingFörfrågan bearbetas fortfarande.

completedGenereringen är klar. Utdata är tillgängliga.

succeededGenereringen lyckades. Utdata är tillgängliga.

failedGenereringen misslyckades. Kontrollera error-fältet.

Slutfört svar

{
  "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"
  }
}

Ladda upp filer

Ladda upp filer till Atlas Cloud-lagring och få en URL som du kan använda i dina API-förfrågningar. Använd multipart/form-data för uppladdning.

POST/api/v1/model/uploadMedia

Uppladdningsexempel

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}")

Svar

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Input Schema

Följande parametrar accepteras i förfrågningsinnehållet.

Totalt: 0Obligatorisk: 0Valfri: 0

Inga parametrar tillgängliga.

Exempel på förfrågningsinnehåll

json

{
  "model": "kwaivgi/kling-video-o3-std/reference-to-video"
}

Output Schema

API:et returnerar ett prediction-svar med de genererade utdata-URL:erna.

idstringrequired

Unique identifier for the prediction.

statusstringrequired

Current status of the prediction.

processingcompletedsucceededfailed

modelstringrequired

The model used for generation.

outputsarray[string]

Array of output URLs. Available when status is "completed".

errorstring

Error message if status is "failed".

metricsobject

Performance metrics.

predict_timenumber

Time taken for video generation in seconds.

created_atstringrequired

ISO 8601 timestamp when the prediction was created.

Format: date-time

completed_atstring

ISO 8601 timestamp when the prediction was completed.

Format: date-time

Exempelsvar

json

{
  "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 integrerar 300+ AI-modeller direkt i din AI-kodassistent. Ett kommando för att installera, sedan använd naturligt språk för att generera bilder, videor och chatta med LLM.

Stödda klienter

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ stödda klienter

Installera

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

Konfigurera API Key

Hämta din API key från Atlas Cloud-instrumentpanelen och ställ in den som en miljövariabel.

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

Funktioner

När det är installerat kan du använda naturligt språk i din AI-assistent för att komma åt alla Atlas Cloud-modeller.

BildgenereringGenerera bilder med modeller som Nano Banana 2, Z-Image och fler.

VideoskapandeSkapa videor från text eller bilder med Kling, Vidu, Veo m.fl.

LLM-chattChatta med Qwen, DeepSeek och andra stora språkmodeller.

MediauppladdningLadda upp lokala filer för bildredigering och bild-till-video-arbetsflöden.

Läs mer

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server ansluter din IDE med 300+ AI-modeller via Model Context Protocol. Fungerar med alla MCP-kompatibla klienter.

Stödda klienter

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ stödda klienter

Installera

bash

npx -y atlascloud-mcp

Konfiguration

Lägg till följande konfiguration i din IDE:s MCP-inställningsfil.

json

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Tillgängliga verktyg

atlas_generate_imageGenerera bilder från textpromptar.

atlas_generate_videoSkapa videor från text eller bilder.

atlas_chatChatta med stora språkmodeller.

atlas_list_modelsBläddra bland 300+ tillgängliga AI-modeller.

atlas_quick_generateInnehållsskapande i ett steg med automatiskt modellval.

atlas_upload_mediaLadda upp lokala filer för API-arbetsflöden.

Läs mer

github.com/AtlasCloudAI/mcp-server

API Schema

Schema ej tillgängligt

Logga in för att visa förfrågningshistorik

Du måste vara inloggad för att få tillgång till din modellförfrågningshistorik.

Logga In

Kling Video O3 Std Reference-to-Video

Kling Video O3 Standard Reference-to-Video generates new videos guided by reference images and an optional reference video, maintaining consistent characters, styles, and scenes. Describe a scenario involving the people or elements in your reference images — the model brings them together in a coherent, natural video. Supports flexible duration, aspect ratio control, and optional sound generation.

Why Choose This?

Character-consistent generation Upload reference images of specific people or elements, and the model preserves their identity throughout the generated video.

Multi-reference support Provide multiple reference images to combine different characters, styles, or elements in one scene.

Optional reference video Supply a reference video for motion guidance, style transfer, or scene continuity.

Sound options Keep original audio from a reference video, or generate new synchronized sound effects.

Flexible output Multiple aspect ratios (16:9, 9:16, 1:1, etc.) and duration from 3 to 15 seconds.

Parameters

Parameter	Required	Description
prompt	Yes	Text description of the desired scene and action
video	No	Reference video for motion or style guidance
images	No	Reference images of characters, elements, or styles
keep_original_sound	No	Keep the original sound from the reference video (default: enabled)
sound	No	Generate synchronized audio for the video (default: disabled)
aspect_ratio	No	Video aspect ratio (default: 16:9)
duration	No	Video length: 3–15 seconds (default: 5)

How to Use

Run — submit and download your video.
Set sound preference — keep original audio from the reference video, or enable generated sound.
Set duration — choose any length from 3 to 15 seconds.
Choose aspect ratio — select the format that fits your platform.
Add reference video (optional) — provide a video for motion or style guidance.
Add reference images — upload images of the characters, objects, or styles you want in the video.
Write your prompt — describe the scene, referencing the characters or elements in your images (e.g., "The man in Figure 2 is walking with the woman in Figure 1 in the park.").

Best Use Cases

Style Transfer — Use a reference video to guide the motion and visual style of new content.
Creative Concepting — Combine multiple characters or elements into new scenarios for rapid ideation.
Marketing & Ads — Generate brand ambassador or spokesperson videos from still photos.
Social Media Content — Produce personalized short-form videos with consistent character identity.
Character-Driven Storytelling — Create scenes starring specific characters from your reference images.

Pro Tips

Match aspect ratio to your target platform: 16:9 for YouTube, 9:16 for TikTok/Reels.
Use shorter durations (3–5 s) for testing character consistency before generating longer clips.
Adding a reference video significantly enhances motion quality.
Use "Figure 1", "Figure 2" etc. in your prompt to refer to specific reference images in order.
Reference images with clear faces and distinct features produce the best character consistency.

Notes

Ensure uploaded URLs are publicly accessible.
Duration supports any value from 3 to 15 seconds.
Prompt is the only required field, but reference images are recommended for best results.

Kling Video O3 Std Video Edit — Edit existing videos with natural-language instructions.
Kling Video O3 Std Text-to-Video — Generate videos from text prompts at Standard pricing.
Kling Video O3 Std Image-to-Video — Animate a single image into video at Standard pricing.
Kling Video O3 Pro Reference-to-Video — Maximum quality reference-to-video with O3 Pro tier.