Seedance Pro’s image-to-video mode transforms still visuals into cinematic motion, maintaining visual consistency and expressive animation across frames.
Seedance Pro’s image-to-video mode transforms still visuals into cinematic motion, maintaining visual consistency and expressive animation across frames.
आपके अनुरोध की लागत 0.011 प्रति रन होगी। $10 के साथ आप इस मॉडल को लगभग 909 बार चला सकते हैं।
आगे आप यह कर सकते हैं:
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": "bytedance/seedance-v1-pro-fast/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()अपने मॉडल अनुरोध इतिहास तक पहुंचने के लिए आपको साइन इन करना होगा।
साइन इन करेंByteDance Seedance V1 Pro I2V Fast is an advanced image-to-video model designed for coherent, multi-shot storytelling with exceptional stability and prompt accuracy. Powered by ByteDance’s latest video foundation framework, it transforms a single image and description into smooth, cinematic motion sequences — ideal for creators, studios, and advertisers who demand both speed and visual fidelity.
🎞️ Coherent Multi-Shot Motion Generates videos that maintain consistent characters, backgrounds, and lighting across complex motion sequences.
🚀 Fast & Efficient Rendering Optimized for rapid generation, offering high-quality output at lower latency compared to standard models.
🧠 Accurate Prompt Following Handles detailed action descriptions, perspective shifts, and multi-stage motion transitions with semantic precision.
🎨 Style Preservation Keeps the original artistic tone, color, and atmosphere of the input image while introducing realistic or stylized movement.
📸 Resolution Flexibility Supports 480p, 720p, and 1080p outputs — balancing speed, cost, and detail to suit different production needs.
| Parameter | Description |
|---|---|
| prompt* | Describe the scene, motion, and style (e.g., “Cinematic pan across a city skyline as a woman turns and smiles toward the camera.”). |
| image* | Upload a static image (JPG / PNG) that defines composition, character, or lighting. |
| duration | Video length in seconds (3–10s). |
| resolution | Choose between 480p (faster, cheaper) or 720p / 1080p (higher detail). |
For optimal video results, it is recommended that the specified video aspect ratio closely matches the original aspect ratio of your uploaded image.