Text to Image
Create AI images from text prompts
ByteDance/seedance-v2.0-mini-reference-to-video
seedance-v2.0-mini-reference-to-video
Generate reference-guided videos with Seedance 2.0 Mini using images, videos, and audio, optional sound, flexible duration, and affordable ByteDance output.
Reference to Video
Related Seedance 2.0 Mini Models
API Examples
Submit Example
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
method: 'POST',
headers: {
Authorization: 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model_name: 'seedance-v2.0-mini-reference-to-video',
prompt:
'Use <<<image_1>>> as the character and visual reference, follow the camera movement in <<<video_1>>>, and synchronize the scene with <<<audio_1>>>.',
images: ['https://example.com/character-reference.jpg'],
videos: ['https://example.com/motion-reference.mp4'],
audios: ['https://example.com/audio-reference.mp3'],
resolution: '720p',
duration: 8,
aspect_ratio: '16:9',
sound: true,
}),
});
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={
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json',
},
json={
'model_name': 'seedance-v2.0-mini-reference-to-video',
'prompt': 'Use <<<image_1>>> as the character and visual reference, follow the camera movement in <<<video_1>>>, and synchronize the scene with <<<audio_1>>>.',
'images': ['https://example.com/character-reference.jpg'],
'videos': ['https://example.com/motion-reference.mp4'],
'audios': ['https://example.com/audio-reference.mp3'],
'resolution': '720p',
'duration': 8,
'aspect_ratio': '16:9',
'sound': True,
},
)
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 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model_name": "seedance-v2.0-mini-reference-to-video",
"prompt": "Use <<<image_1>>> as the character and visual reference, follow the camera movement in <<<video_1>>>, and synchronize the scene with <<<audio_1>>>.",
"images": ["https://example.com/character-reference.jpg"],
"videos": ["https://example.com/motion-reference.mp4"],
"audios": ["https://example.com/audio-reference.mp3"],
"resolution": "720p",
"duration": 8,
"aspect_ratio": "16:9",
"sound": true
}'
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
Seedance 2.0 Mini Reference to Video Pricing
| Parameters | Price | Original Price | Discount |
|---|
Related Models
seedream-v4.5text-to-imageseedream-v4.5-editimage-to-imageseedream-v5.0text-to-imageseedream-v5.0-editimage-to-imageseedream-v5.0-protext-to-imageseedream-v5.0-pro-editimage-to-imageseedance-v1.5-pro-text-to-videotext-to-videoseedance-v1.5-pro-image-to-videoimage-to-videoseedance-v2.0-text-to-videotext-to-videoseedance-v2.0-image-to-videoimage-to-videoseedance-v2.0-reference-to-videoreference-to-videoseedance-v2.0-fast-text-to-videotext-to-videoseedance-v2.0-fast-image-to-videoimage-to-videoseedance-v2.0-fast-reference-to-videoreference-to-videoseedance-v2.0-mini-text-to-videotext-to-videoseedance-v2.0-mini-image-to-videoimage-to-videoseedance-v2.0-mini-reference-to-videoreference-to-videoseedance-v2.5-text-to-videotext-to-videoseedance-v2.5-image-to-videoimage-to-videoseedance-v2.5-reference-to-videoreference-to-videoREADME
Seedance V2.0 Mini Reference-to-Video API for Affordable Multimodal Video Generation
Seedance V2.0 Mini Reference-to-Video is ByteDance's cost-effective model for generating videos from image, video, and audio references. It combines multimodal guidance with flexible output controls, making it suitable for creators and developers who need consistent visual direction without the higher-resolution output of the standard Seedance V2.0 model.
Key Features of Seedance V2.0 Mini Reference-to-Video
- Multimodal Reference Guidance: Guide a generation with images, videos, and audio clips in one request.
- Flexible Reference Inputs: Use 1-9 images, up to 3 videos, and up to 3 audio clips. Images may be omitted when at least one reference video is supplied.
- Reference-Aware Prompting: Address uploaded media directly in the prompt with numbered image, video, and audio placeholders.
- Practical Output Resolutions: Generate at 480p or 720p for cost-conscious production workflows.
- Flexible Video Duration: Create clips from 4 to 15 seconds.
- Multiple Aspect Ratios: Choose from 21:9, 16:9, 9:16, 1:1, 4:3, and 3:4.
- Optional Generated Sound: Sound is enabled by default and can be disabled when a silent result is preferred.
- No Seed Parameter: Seedance V2.0 Mini models do not support seed control.
How to Use Seedance V2.0 Mini Reference-to-Video
- Write a Prompt: Describe the intended scene, motion, camera behavior, timing, and relationship between the supplied references.
- Add Visual References: Upload at least one image or video. You can provide 1-9 images and 0-3 videos; an empty image list is valid only when a reference video is present.
- Add Optional Audio References: Upload up to 3 audio clips when sound, rhythm, speech, or timing should influence the output.
- Reference Media in the Prompt: Use numbered placeholders such as image 1, video 1, and audio 1 through the API placeholder syntax shown in the API documentation.
- Configure the Output: Select 480p or 720p, a duration from 4-15 seconds, and one of the six supported aspect ratios.
- Choose Whether to Generate Sound: Keep sound enabled by default or disable it for silent video generation.
- Submit the Request: Send the request to the video task API and use the returned task identifier to check generation status.
When one or more reference videos are uploaded, the generation charge is doubled once. The multiplier is the same regardless of the number or duration of the uploaded reference videos.
Best Use Cases for Seedance V2.0 Mini Reference-to-Video
- Character and Product Continuity: Use reference images or clips to preserve recognizable visual direction across new scenes.
- Social Media Video: Produce vertical, square, landscape, or cinematic clips for common publishing formats.
- Motion and Camera Guidance: Use a reference video to communicate movement, pacing, composition, or camera behavior.
- Audio-Guided Creation: Align generated visuals with supplied music, speech, sound effects, or timing cues.
- Rapid Creative Exploration: Test multimodal concepts at 480p or 720p before committing to higher-resolution production.
Note: Every request must include at least one image or video reference. Each uploaded video and audio clip must be between 2 and 15 seconds long. Audio-only requests are not supported.
Seedance V2.0 Mini Reference-to-Video vs Competitors
- Compared with Seedance V2.0 Reference-to-Video: Both support image, video, and audio guidance, while the Mini model focuses on affordable 480p and 720p output instead of the standard model's higher-resolution options.
- Compared with Wan 2.7 Reference-to-Video: Seedance V2.0 Mini supports separate image, video, and audio reference arrays and generated sound, while omitting seed control.
- Compared with Vidu Q3 Reference-to-Video: Seedance V2.0 Mini extends reference guidance beyond images by accepting video and audio inputs.
- Compared with Seedance V2.0 Mini Text-to-Video: Text-to-Video generates from a prompt alone, while Reference-to-Video adds image, video, and optional audio inputs for multimodal guidance.
- Compared with Runway's Video Models: Seedance V2.0 Mini provides a direct reference-to-video API for teams that want image, video, and audio guidance in one request.
Use the Seedance 2.0 Mini 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