
Kling v2.6 Pro Motion Control API by Kuaishou
Kling 2.6 Pro Motion Control turns reference motion clips (dance, action, gesture) into smooth, realistic animations. Upload a character image (or source video) and a motion video; the model transfers the movement while preserving identity and temporal consistency.
Entrée
Sortie
InactifVotre requête coûtera $0.095 par exécution. Avec $10, vous pouvez exécuter ce modèle environ 105 fois.
Vous pouvez continuer avec :
Exemple de code
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/motion-control",
"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()Installer
Installez le package requis pour votre langage.
pip install requestsAuthentification
Toutes les requêtes API nécessitent une authentification via une clé API. Vous pouvez obtenir votre clé API depuis le tableau de bord Atlas Cloud.
export ATLASCLOUD_API_KEY="your-api-key-here"En-têtes HTTP
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}N'exposez jamais votre clé API dans du code côté client ou dans des dépôts publics. Utilisez plutôt des variables d'environnement ou un proxy backend.
Soumettre une requête
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())Soumettre une requête
Soumettez une requête de génération asynchrone. L'API renvoie un identifiant de prédiction que vous pouvez utiliser pour vérifier le statut et récupérer le résultat.
/api/v1/model/generateVideoCorps de la requête
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-v2.6-pro/motion-control",
"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']}")Réponse
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Vérifier le statut
Interrogez le point de terminaison de prédiction pour vérifier le statut actuel de votre requête.
/api/v1/model/prediction/{prediction_id}Exemple d'interrogation
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)Valeurs de statut
processingLa requête est encore en cours de traitement.completedLa génération est terminée. Les résultats sont disponibles.succeededLa génération a réussi. Les résultats sont disponibles.failedLa génération a échoué. Vérifiez le champ d'erreur.Réponse terminée
{
"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"
}
}Télécharger des fichiers
Téléchargez des fichiers vers le stockage Atlas Cloud et obtenez une URL utilisable dans vos requêtes API. Utilisez multipart/form-data pour le téléchargement.
/api/v1/model/uploadMediaExemple de téléchargement
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}")Réponse
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Schema d'entrée
Les paramètres suivants sont acceptés dans le corps de la requête.
Aucun paramètre disponible.
Exemple de corps de requête
{
"model": "kwaivgi/kling-v2.6-pro/motion-control"
}Schema de sortie
L'API renvoie une réponse de prédiction avec les URL des résultats générés.
Exemple de réponse
{
"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 intègre plus de 300 modèles d'IA directement dans votre assistant de codage IA. Une seule commande pour installer, puis utilisez le langage naturel pour générer des images, des vidéos et discuter avec des LLM.
Clients pris en charge
Installer
npx skills add AtlasCloudAI/atlas-cloud-skillsConfigurer la clé API
Obtenez votre clé API depuis le tableau de bord Atlas Cloud et définissez-la comme variable d'environnement.
export ATLASCLOUD_API_KEY="your-api-key-here"Fonctionnalités
Une fois installé, vous pouvez utiliser le langage naturel dans votre assistant IA pour accéder à tous les modèles Atlas Cloud.
Serveur MCP
Le serveur MCP Atlas Cloud connecte votre IDE avec plus de 300 modèles d'IA via le Model Context Protocol. Compatible avec tout client compatible MCP.
Clients pris en charge
Installer
npx -y atlascloud-mcpConfiguration
Ajoutez la configuration suivante au fichier de paramètres MCP de votre IDE.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Outils disponibles
Schéma API
Schéma non disponibleAucun exemple disponible
Veuillez vous connecter pour voir l'historique des requêtes
Vous devez vous connecter pour accéder à l'historique de vos requêtes de modèle.
Se ConnecterKling v2.6 Pro Motion Control
Kling v2.6 Pro Motion Control is Kuaishou's advanced motion transfer model that animates a reference image by applying the movement from a reference video. Upload a character image and a motion clip (like a dance or action sequence), and the model extracts the motion path to generate smooth, realistic video where your subject performs those exact movements.
Key capabilities
- Motion extraction and transfer Upload a 3 to 30-second reference video showing any movement (dance, walk cycle, martial arts, gestures), and the model captures the full motion sequence frame-by-frame to apply it to your image.
- Full-body motion accuracy The system captures detailed movements including posture, limb positions, and complex actions, ensuring smooth and natural-looking animation even for fast or intricate sequences.
- Flexible character orientation control Choose whether the final video follows the reference image's aspect ratio and composition ("image" mode) or the reference video's framing ("video" mode), with duration limits adjusted accordingly.
- Audio preservation option Retain the original audio from your reference video or generate silent output, giving you control over the final soundscape.
- Prompt-guided refinement Use text prompts to adjust scene details, styling, lighting, and atmosphere while maintaining the core motion transfer from the reference video.
Parameters and how to use
- image: (required) The reference image showing the subject you want to animate
- video: (required) The reference video containing the motion sequence to transfer
- character_orientation: (required) Controls output framing and duration limits
- prompt: Text description to refine scene details, style, and atmosphere
- keep_original_sound: Whether to preserve audio from the reference video
- negative_prompt: Elements to avoid in the generated video
How to use
- Prompt
Describe the scene setting, visual style, lighting, and atmosphere you want while the motion is being transferred. The model will apply your reference video's movement to your reference image, so focus your prompt on environmental details rather than the action itself.
Example: "cinematic lighting, shallow depth of field, urban street background, golden hour, film grain"
Media requirements
Images
- Max file size: 10 MB
- Tip: Use clear, well-lit images showing the full subject for best motion transfer results
Videos
- Duration limits depend on character_orientation setting (see below)
Other parameters
- character_orientation – (required) Choose one:
image – Output matches the reference image's framing and composition. video – Output matches the reference video's framing and composition. Reference video can be up to 30 seconds.
- keep_original_sound – Boolean, defaults to true
true – Preserve audio from the reference video false – Generate silent video output
- negative_prompt – Optional text to specify unwanted elements like "blurry, distorted, watermark, low quality, flickering". Max 2,500 characters.
After you finish configuring the parameters, click Run, preview the result, and iterate if needed.
Pricing
| Duration (s) | Billed Duration (s) | Total Price (USD) |
|---|---|---|
| 5 | 5 | $0.560 |
| 10 | 10 | $1.120 |
| 15 | 15 | $1.680 |
| 30 | 30 | $3.360 |
Notes
Best practices:
- For complex movements like dance or martial arts, use reference videos between 3 and 10 seconds showing clear, unobstructed motion
- Ensure your reference image shows the subject in good lighting with minimal occlusion
- Start with the default settings and use prompts primarily for scene styling rather than motion instructions
- The model works best when the reference image subject and reference video subject are similar in type (e.g., both human characters)
Use cases:
- Animate character illustrations with real dance choreography or action sequences
- Create product demonstration videos by transferring human gestures to animated mascots
- Generate character performance clips for storyboarding and concept work
- Produce social media content by applying trending motion clips to custom characters
Related Models
- Kling v2.6 Pro Image-to-Video – Generate videos from a single image with prompt-driven motion and optional native audio.
- Kling v2.6 Pro Text-to-Video – Create videos entirely from text prompts with cinematic visuals and audio–video co-generation.
- Kling Omni Video O1 Reference-to-Video – Maintain subject identity across frames using multi-reference inputs for character-consistent video generation.






