Text to Image
Create AI images from text prompts
Alibaba/wan-3.0-reference-to-video
wan-3.0-reference-to-video
Free to try Alibaba Wan 3.0 API for Reference-to-Video and guide video generation with images, clips, audio, documents, or webpages on Flaq AI. Explore flexible creation.
Reference to Video
Related Wan 3.0 Models
API Examples
Submit Example
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
body: JSON.stringify({
model_name: 'wan-3.0-reference-to-video',
prompt: 'Use the references to create a cinematic product launch with coordinated motion and sound',
duration: 12,
resolution: '1080p',
aspect_ratio: '16:9',
sound: true,
images: ['https://example.com/product-reference.jpg'],
videos: ['https://example.com/motion-reference.mp4'],
audios: ['https://example.com/sound-reference.mp3'],
files: ['https://example.com/creative-brief.pdf'],
seed: 42
})
});
const { data } = await response.json();
const taskId = data.task_id;
Polling Example
// Step 2: Poll for results
const taskId = data.task_id;
const pollResult = async (taskId) => {
const res = await fetch(`https://api.flaq.ai/api/v1/video/${taskId}`, {
headers: { 'Authorization': 'Bearer YOUR_API_KEY' }
});
return res.json();
};
while (true) {
const pollResultData = await pollResult(taskId);
const status = pollResultData.data.task_status;
if (status === 'succeed') {
console.log(pollResultData.data.task_result.videos[0].url);
break;
}
if (status === 'failed') {
console.error(pollResultData.data.task_status_msg);
break;
}
await new Promise(resolve => setTimeout(resolve, 10000));
}
Submit Example
import requests
response = requests.post(
'https://api.flaq.ai/api/v1/video/task',
headers={
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
json={
'model_name': 'wan-3.0-reference-to-video',
'prompt': 'Use the references to create a cinematic product launch with coordinated motion and sound',
'duration': 12,
'resolution': '1080p',
'aspect_ratio': '16:9',
'sound': True,
'images': ['https://example.com/product-reference.jpg'],
'videos': ['https://example.com/motion-reference.mp4'],
'audios': ['https://example.com/sound-reference.mp3'],
'files': ['https://example.com/creative-brief.pdf'],
'seed': 42
}
)
result = response.json()
task_id = result['data']['task_id']
Polling Example
# Step 2: Poll for results
task_id = response.json()['data']['task_id']
poll_url = f"https://api.flaq.ai/api/v1/video/{task_id}"
while True:
poll_result = requests.get(poll_url, headers={'Authorization': 'Bearer YOUR_API_KEY'}).json()
status = poll_result['data']['task_status']
if status == 'succeed':
print(poll_result['data']['task_result']['videos'][0]['url'])
break
if status == 'failed':
print(poll_result['data']['task_status_msg'])
break
time.sleep(10)
Submit Example
curl -X POST https://api.flaq.ai/api/v1/video/task \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model_name": "wan-3.0-reference-to-video",
"prompt": "Use the references to create a cinematic product launch with coordinated motion and sound",
"duration": 12,
"resolution": "1080p",
"aspect_ratio": "16:9",
"sound": true,
"images": ["https://example.com/product-reference.jpg"],
"videos": ["https://example.com/motion-reference.mp4"],
"audios": ["https://example.com/sound-reference.mp3"],
"files": ["https://example.com/creative-brief.pdf"],
"seed": 42
}'
Polling Example
# Step 2: Poll for results
# Replace {task_id} with the task_id returned from the submit response
curl -X GET "https://api.flaq.ai/api/v1/video/{task_id}" \
-H "Authorization: Bearer YOUR_API_KEY"
Try the AI Video Generator now
Wan 3.0 Reference to Video Pricing
| Parameters | Price | Original Price | Discount |
|---|
Related Models
qwen-image-2.0text-to-imageqwen-image-2.0-editimage-to-imageqwen-image-2.0-protext-to-imageqwen-image-2.0-pro-editimage-to-imageqwen-image-lora-editimage-to-imagez-imagetext-to-image
happyhorse-1.0-text-to-videotext-to-videohappyhorse-1.0-image-to-videoimage-to-videohappyhorse-1.1-text-to-videotext-to-videohappyhorse-1.1-image-to-videoimage-to-videohappyhorse-1.1-reference-to-videoreference-to-videowan-2.7-text-to-videotext-to-videowan-2.7-image-to-videoimage-to-videowan-2.7-lora-image-to-videoimage-to-videowan-2.7-video-editvideo-editwan-2.7-reference-to-videoreference-to-videowan-v2.7-imagetext-to-imagewan-v2.7-image-editimage-to-imagewan-v2.7-image-protext-to-imagewan-v2.7-image-pro-editimage-to-imagewan-2.6-text-to-videotext-to-videowan-2.6-image-to-videoimage-to-videoqwen-image-3.0text-to-imageqwen-image-3.0-editimage-to-imageqwen-image-3.0-protext-to-imageqwen-image-3.0-pro-editimage-to-imagewan-3.0-text-to-videotext-to-videowan-3.0-image-to-videoimage-to-videowan-3.0-video-editvideo-editwan-3.0-reference-to-videoreference-to-videoqwen-3.7-max-text-to-texttext-to-textqwen-3.7-plus-text-to-texttext-to-textqwen-3.7-max-web-searchweb-searchqwen-3.7-plus-web-searchweb-searchqwen-plus-charactertext-to-textqwen-flash-charactertext-to-textqwen-3.8-max-text-to-texttext-to-textqwen-3.8-max-web-searchweb-searchREADME
Wan 3.0 API for Reference-to-Video (Multimodal Video Direction)
Wan 3.0 API for Reference-to-Video generates video from a prompt with optional image, video, audio, document, or public webpage references. Developers can use the supported inputs to guide visual identity, motion, sound, context, and scene direction while configuring duration, resolution, aspect ratio, sound, and seed. Flaq AI provides a task-based workflow for submitting multimodal requests and retrieving completed videos.
Key Features of Wan 3.0 API for Reference-to-Video
- Multimodal Reference Inputs: Guide a video request with optional images, videos, audio clips, a reference document, or a public webpage.
- Flexible Reference Composition: Combine supported image, video, and audio collections in one request when the creative direction needs several types of context.
- Document and Web Context: Supply one supported document or one public webpage link to add written or structured reference material.
- Prompt-Based Direction: Explain how the supplied references should influence subjects, motion, environment, sound, style, and composition.
- Flexible Video Controls: Configure duration, resolution, aspect ratio, sound preference, and an optional seed for each generation task.
- Production Task Workflow: Submit the request, monitor task status, and retrieve the generated clip for review and downstream use.
How to Use Wan 3.0 API for Reference-to-Video on Flaq AI
- Input: A prompt plus any supported combination of optional image, video, audio, document, or public webpage references.
- Output: A reference-guided video returned through the Flaq AI task workflow for review, storage, editing, or publishing.
- Reference Planning: State the intended role of each supplied asset, such as subject identity, movement, environment, sound, or background context.
- Reference Limits: Validate file formats, dimensions, durations, page counts, and collection limits before submission.
- File or Link Choice: Use either one document or one public webpage link in a request; these two input types are mutually exclusive.
Best Use Cases for Wan 3.0 Reference-to-Video API Integration
- Character and Product Consistency: Use visual references to guide recognizable subjects, products, styling, and presentation across a new sequence.
- Motion and Sound Direction: Combine video and audio references when a concept needs clearer movement, timing, or sound cues.
- Campaign and Brand Workflows: Bring visual assets and creative briefs together for coordinated promotional video generation.
- Storyboard and Shot Development: Anchor composition, movement, atmosphere, and scene progression with selected reference material.
- Knowledge-Guided Creative Tools: Use a document or public webpage as contextual input for applications that translate briefs and source material into video concepts.
Note Reference inputs are optional, but every supplied asset must meet its format and limit requirements. A reference file and webpage link cannot be used together in the same request. Overseas webpage URLs are supported by the overseas service but cannot be parsed by the domestic service.
Wan 3.0 Reference-to-Video vs Competitors: Comparative Analysis
-
Wan 3.0 vs. Wan 2.7 Reference-to-Video
Wan 2.7 focuses on image, video, and voice references with a combined visual-reference limit. Wan 3.0 expands the workflow with independent media limits plus document and public webpage context. -
Wan 3.0 vs. MiniMax H3 Reference-to-Video
MiniMax H3 supports multimodal video direction with visual and audio references. Wan 3.0 adds document and webpage input options for teams working with broader creative source material. -
Wan 3.0 vs. Seedance 2.5 Reference-to-Video
Seedance 2.5 uses image, video, and audio references in its audio-visual generation workflow. Wan 3.0 offers a Wan-family alternative with optional document or public link context. -
Wan 3.0 vs. Kling Video O3 Reference-to-Video
Kling Video O3 spans reference generation and video editing variants. Wan 3.0 provides an Alibaba-oriented multimodal request format with flexible output and sound controls. -
Wan 3.0 vs. Runway References
Runway integrates references into a broad creative workspace. Wan 3.0 is suited to developers building reference-guided generation directly into their own products and automated workflows.
Use the Wan 3.0 Reference to Video Model Directly in Powerful AI Tools
Explore several AI creation tools for quick image and video workflows in your browser, then scale successful ideas with Flaq AI's production-ready model APIs. Flaq AI provides a unified API layer for all models, making it easy to use and scale your workflows.
Image to Image
Create AI images from images and text prompts
Text to Video
Create AI videos from text prompts
Image to Video
Animate images into AI videos
AI Media Creator
Create AI images and videos in one unified workspace
Reference to Video
Create consistent videos from reference media
AI Canvas
Build visual AI image and video workflows on an infinite canvas