
AI 文本转图像生成器
使用领先 AI 图像模型、灵活设置和快速浏览器工作流,从提示词创建精致图像。
免费试用 Vidu Q3 参考素材生成视频 API,支持最多四张参考图片、1080p 输出、可选音效、灵活时长和种子控制。适合灵活的视频创作与测试。
// Step 1: Submit generation request
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: 'viduq3-reference-to-video',
prompt: 'Keep the character from image one and the jacket details from image two while walking through a rainy city',
resolution: '1080p',
duration: 8,
aspect_ratio: '9:16',
images: [
'https://example.com/character-reference.jpg',
'https://example.com/outfit-reference.jpg'
],
sound: true,
seed: 42
})
});
const { data } = await response.json();
const taskId = data.task_id;
// Use the @ (AT) reference feature in prompt through <<<...>>> placeholders.
// Placeholder numbering is 1-based and follows the images array order:
// <<<image_1>>> = images[0], <<<image_2>>> = images[1], <<<image_3>>> = images[2]
const mediaReferenceResponse = 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: 'viduq3-reference-to-video',
prompt: 'Keep the character from <<<image_1>>> wearing the coat from <<<image_2>>> while entering the rainy city shown in <<<image_3>>>, then return to a close-up of <<<image_1>>>',
resolution: '1080p',
duration: 8,
aspect_ratio: '9:16',
images: [
'https://example.com/character-reference.jpg',
'https://example.com/coat-reference.jpg',
'https://example.com/rainy-city-reference.jpg'
],
sound: true,
seed: 42
})
});
const { data: mediaReferenceData } = await mediaReferenceResponse.json();
const mediaReferenceTaskId = mediaReferenceData.task_id;
// 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));
}
# Step 1: Submit generation request
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': 'viduq3-reference-to-video',
'prompt': 'Keep the character from image one and the jacket details from image two while walking through a rainy city',
'resolution': '1080p',
'duration': 8,
'aspect_ratio': '9:16',
'images': [
'https://example.com/character-reference.jpg',
'https://example.com/outfit-reference.jpg'
],
'sound': True,
'seed': 42
}
)
result = response.json()
task_id = result['data']['task_id']
# Use the @ (AT) reference feature in prompt through <<<...>>> placeholders.
# Placeholder numbering is 1-based and follows the images array order:
# <<<image_1>>> = images[0], <<<image_2>>> = images[1], <<<image_3>>> = images[2]
media_reference_response = requests.post(
'https://api.flaq.ai/api/v1/video/task',
headers={
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
json={
'model_name': 'viduq3-reference-to-video',
'prompt': 'Keep the character from <<<image_1>>> wearing the coat from <<<image_2>>> while entering the rainy city shown in <<<image_3>>>, then return to a close-up of <<<image_1>>>',
'resolution': '1080p',
'duration': 8,
'aspect_ratio': '9:16',
'images': [
'https://example.com/character-reference.jpg',
'https://example.com/coat-reference.jpg',
'https://example.com/rainy-city-reference.jpg'
],
'sound': True,
'seed': 42
}
)
media_reference_result = media_reference_response.json()
media_reference_task_id = media_reference_result['data']['task_id']
# 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)
# Step 1: Submit generation request
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": "viduq3-reference-to-video",
"prompt": "Keep the character from image one and the jacket details from image two while walking through a rainy city",
"resolution": "1080p",
"duration": 8,
"aspect_ratio": "9:16",
"images": [
"https://example.com/character-reference.jpg",
"https://example.com/outfit-reference.jpg"
],
"sound": true,
"seed": 42
}'
# Use the @ (AT) reference feature in prompt through <<<...>>> placeholders.
# Placeholder numbering is 1-based and follows the images array order:
# <<<image_1>>> = images[0], <<<image_2>>> = images[1], <<<image_3>>> = images[2]
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": "viduq3-reference-to-video",
"prompt": "Keep the character from <<<image_1>>> wearing the coat from <<<image_2>>> while entering the rainy city shown in <<<image_3>>>, then return to a close-up of <<<image_1>>>",
"resolution": "1080p",
"duration": 8,
"aspect_ratio": "9:16",
"images": [
"https://example.com/character-reference.jpg",
"https://example.com/coat-reference.jpg",
"https://example.com/rainy-city-reference.jpg"
],
"sound": true,
"seed": 42
}'
# 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"
| 参数 | 价格 | 原价 | 折扣 |
|---|
Vidu Q3 Reference-to-Video API 为需要一致角色、对象和场景的开发者与创意团队 提供生产就绪的 AI 视频生成。这项 Reference-to-Video API 集成使用一张或多张参考图像 锚定主体身份,同时生成带有同步原生音频的连贯多镜头视频。它基于 Vidu 新一代 Q3 模型构建,结合智能镜头切换、强大的跨镜头一致性和灵活的输出 控制,为 Flaq AI 上可扩展的叙事工作流提供支持。
注意 请确保提示词和参考图像符合 Vidu 的内容安全准则。如果发生错误, 请检查输入中是否含有受限内容,进行调整后重试。
Vidu Q3 Reference-to-Video 与 Vidu Q3 Image-to-Video 对比 Vidu Q3 Image-to-Video 可让起始图像动起来。Vidu Q3 Reference-to-Video 使用多个主体参考素材,在内容更丰富的多镜头 叙事生成中保持身份和连续性。
Vidu Q3 Reference-to-Video 与 Vidu Q3 Turbo Reference-to-Video 对比 Vidu Q3 Turbo 优先追求极致速度和成本 效率。Vidu Q3 侧重在不同机位间实现更强的一致性,并为叙事、品牌和 角色工作流提供均衡的制作质量。
Vidu Q3 Reference-to-Video 与 Seedance V2.0 Reference-to-Video 对比 Seedance V2.0 支持广泛的混合模态 参考输入。Vidu Q3 通过多图像主体锚定、智能镜头切换,以及 紧密同步的原生对话、音效和音乐展现差异化优势。
Vidu Q3 Reference-to-Video 与 Wan 2.7 Reference-to-Video 对比 Wan 2.7 支持混合图像、视频和可选声音 参考素材。Vidu Q3 侧重高效的多图像一致性、原生音视频输出,以及跨镜头变化的连贯 叙事。
Vidu Q3 Reference-to-Video 与 Kling Video O3 Reference-to-Video 对比 Kling Video O3 提供强大的参考素材引导 动作与场景推理。Vidu Q3 提供多图像主体一致性、原生多语言音频和智能 镜头切换,用于创作完整的视听故事。
在浏览器中探索多种 AI 创作工具,用于快速图像和视频工作流,然后通过 Flaq AI 可用于生产的模型 API 扩展成功创意。Flaq AI 为所有模型提供统一 API 层,让你的工作流更容易使用和扩展。