Kling v3.0 Professional Image-to-Video model by Kuaishou. Premium quality video generation from images with advanced features.
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-v3.0-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()Kling V3.0 Pro Image-to-Video
Kling V3.0 Pro Image-to-Video is Kuaishou's highest-quality image-to-video model. Upload a reference image and describe the motion — the model generates cinematic-grade video with superior visual fidelity, optional synchronized sound, voice support, and start-to-end frame guidance.
Why Choose This?
Pro-tier quality Superior visual detail, motion smoothness, and cinematic rendering compared to Standard.
Start-end frame guidance Optional end image for controlled transitions between two frames.
Sound generation Optional synchronized sound effects generated alongside the video.
Voice list support Add up to 2 custom voice entries for character dialogue.
CFG scale control Fine-tune the balance between prompt adherence and creative freedom.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | No | Text description of the desired motion and action |
| negative_prompt | No | Elements to exclude from generation |
| image | Yes | Start frame image to animate (URL or upload) |
| end_image | No | End frame image for guided transitions |
| duration | No | Video length: 5 or 10 seconds (default: 5) |
| cfg_scale | No | Prompt adherence strength (default: 0.5) |
| sound | No | Generate synchronized sound (default: disabled) |
| voice_list | No | Custom voice entries, up to 2 (click "+ Add Item") |
How to Use
- Run — submit and download your video.
- Add voices (optional) — add up to 2 voice entries for dialogue.
- Enable sound (optional) — generate synchronized audio with the video.
- Adjust cfg_scale (optional) — higher for stricter prompt following, lower for more freedom.
- Set duration — 5 seconds or 10 seconds.
- Add negative prompt (optional) — specify what you want to avoid.
- Upload end image (optional) — provide an end frame for guided transitions.
- Write your prompt (optional) — describe the motion, camera movement, and action.
- Upload your image — provide the reference image to animate.
Best Use Cases
- Brand Content — Polished visual storytelling from still imagery.
- Short Films — Create film-quality animated scenes with dialogue.
- Professional Marketing — Premium promotional videos with sound from product photos.
- Scene Transitions — Use start and end frames for smooth cinematic transitions.
- High-End Photo Animation — Bring images to life with maximum visual quality.
Pro Tips
- Use Standard tier for drafts and testing, Pro for final production.
- Lower cfg_scale for more creative variation, higher for strict prompt adherence.
- Use negative prompts to avoid artifacts (e.g., "blurry, low quality, distorted").
- Enable sound for a complete video experience with synchronized audio.
- Add an end_image for controlled transitions between two visual states.
- Use clear, descriptive prompts with specific motion and cinematography details.
Notes
- Ensure uploaded image URLs are publicly accessible.
- Voice list supports a maximum of 2 entries.
- Duration options are 5 or 10 seconds only.
- Image is the only required field; prompt is optional but recommended.
Related Models
- Kling V3.0 Standard Text-to-Video — Standard tier text-to-video.
- Kling V3.0 Standard Image-to-Video — Standard tier at lower cost.
- Kling V3.0 Pro Text-to-Video — Pro quality text-to-video generation.
详细规格
概览：
模型提供商：KUAISHOU
模型类型：image-to-video
部署方式：推理 API；Playground
定价：$0.204
关键参数：
尺寸上限：最大宽度 × 高度（用户可配置）
LoRA 支持：否
种子选项：N/A
