kwaivgi/kling-v2.6-pro/image-to-video

इमेज-से-वीडियो

PRO

Latest image-to-video model from Kuaishou with sound generation, enhanced dynamics, and cinematic quality.

इनपुट

पैरामीटर कॉन्फ़िगरेशन लोड हो रहा है...

आउटपुट

निष्क्रिय

जेनरेट किए गए वीडियो यहां दिखाई देंगे

अपनी सेटिंग्स कॉन्फ़िगर करें और शुरू करने के लिए चलाएं पर क्लिक करें

आपके अनुरोध की लागत 0.06 प्रति रन होगी। $10 के साथ आप इस मॉडल को लगभग 166 बार चला सकते हैं।

आगे आप यह कर सकते हैं:

वीडियो अपस्केलर वीडियो विस्तार

1. कोड उदाहरण

2. स्कीमा

3. LLM प्रॉम्प्ट

4. पैरामीटर

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-v2.6-pro/image-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()

अनुरोध इतिहास देखने के लिए कृपया साइन इन करें

अपने मॉडल अनुरोध इतिहास तक पहुंचने के लिए आपको साइन इन करना होगा।

साइन इन करें

Kling 2.6 Audio Model - Image to Video

Kling 2.6 introduces audio–video co-generation for the very first time, pairing superb visuals with natural, native audio to deliver a fully coherent, immersive experience — more than just a video clip.

Model Highlights

Audio–video co-generation introduced for the very first time in the Kling series.
Voices that sync flawlessly with the character — natural, native, and instantly immersive.
Generates an entire experience, not just a clip — coherent looking & sounding output that opens up rich narrative possibilities.
When superb visuals are paired with natural voiceovers, matching sound effects, and immersive ambient sounds, the 2.6 model generates coherent looking & sounding outputs as an entire experience — more than a video clip.

Aspect Ratios

Kling 2.6 supports the following aspect ratios:

16:9 – Standard landscape video (YouTube, web, most displays)
9:16 – Vertical video (TikTok, Reels, Shorts, Stories)
1:1 – Square video (feeds, social posts, ads)

Use Cases

Marketing and launch videos with native, character-synced voiceover.
Storytelling and narrative content where visuals and audio must feel like one.
Product explainers and demo videos with both strong visuals and natural narration.
Cinematic social media content with immersive ambient sound and effects.

Price

Without Audio 5s video – $0.35
Without Audio 10s video – $0.70
With Audio 5s video – $0.70
With Audio 10s video – $1.40

How to Use

Describe your desired scene, characters, motion, and audio mood (voiceover tone, ambience, SFX).
Choose an aspect ratio (16:9, 9:16, or 1:1) and configure video duration (e.g., 5s or 10s).
Run generation to create a coherent audio–video experience — See the Sound, Hear the Visual.
Refine and regenerate as needed for alternative versions or platforms.