元极未来 灵创万物
文生视频、图生视频、多模态参考三大模式，精准控制角色一致性与镜头语言。
输入文字描述，AI 自动生成高质量视频。支持场景、人物、动作等多维度控制
上传静态图片，生成流畅的视频动画。精准的角色一致性控制，适用于漫画、插画等场景
粘贴小说文本，AI 自动提取场景、对白、角色动作，生成结构化剧本和分镜脚本
POST https://yjyl.ai/v1/chat/completions
Authorization: Bearer sk-••••••••
Content-Type: application/json
{
"model": "claude-fable-5-1",
"messages": [
{
"role": "user",
"content": "Hello, GengXi."
}
],
"temperature": 0.7,
"max_tokens": 2048,
"top_p": 1,
"stream": false
}POST https://yjyl.ai/v1/images/generations
Authorization: Bearer sk-••••••••
Content-Type: application/json
{
"model": "flux-pro",
"prompt": "A serene mountain landscape at sunset, with golden light illuminating the peaks",
"negative_prompt": "blurry, low quality, distorted",
"size": "1024x1024",
"quality": "hd",
"n": 1,
"style": "natural",
"response_format": "url"
}POST https://yjyl.ai/v1/videos
Authorization: Bearer sk-••••••••
Content-Type: application/json
{
"model": "seedance-2.5",
"prompt": "一只橘猫在月光下的屋顶漫步，星空闪烁，城市灯火在远处若隐若现",
"duration": 5,
"resolution": "1080p",
"fps": 30,
"aspect_ratio": "16:9",
"motion_level": 3,
"seed": 42
}从一包话、一张图，到可以从续生产的漫剧镜头。元灵把Seedance视频与统一API放进同一条创作路径。