Click to upload or drag and drop images.
Images: JPEG/JPG/PNG/WebP, Max 20MB
Describe the image you want to generate.
0/20000Click to upload or drag and drop
Supported formats: JPEG, PNG, WEBP, JPG Maximum file size: 20MB; Maximum files: 7
Upload an image file to use as input for the API
Note: when video input is provided, the output duration is determined by the model automatically. This duration parameter will not take effect.
Audio ID list. Up to 3 ID is allowed.
Video ratio
Character ID list. Each character ID uses 1 or 2 image slot. Available character slots: 3/7. Remaining image slots: 5/7.
Output video resolution. Valid values: 720P(default), 1080P, 4k.
Optional video input. Only 1 video is allowed and it uses 2 image slots.
Random seed. Range: [0, 2147483647]. If not specified, the system generates a seed automatically. Fixing the seed can improve reproducibility, but results may still vary due to the model’s stochasticity.
Explore different use cases and parameter configurations
Basic Voice
Input description
Textarea description
0/20000Input description
No result yet. Click generate to start.
Input description
Click to upload or drag and drop
Supported formats: JPEG, PNG, WEBP Maximum file size: 20MB; Maximum files: 2
Array of character reference image URLs. Up to 2 images are supported. Index 0 is the portrait image, and index 1 is the body image. The body image is optional, but if provided, the portrait image must be present at index 0.
Audio ID list. Up to 1 IDs are allowed.
Character Description
0/20000No result yet. Click generate to start.
README
Complete guide to using Gemini Omni 1.1 Flash
面向多模态视频生成与编辑的 Gemini Omni 1.1 Flash API

curl https://api.kie.ai/api/v1/jobs/createTask \-H "Authorization: Bearer $KIE_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "google/gemini-omni-flash-1-1","input": {"prompt": "A drone shot gliding over a misty pine forest at sunrise","duration": "4","aspect_ratio": "16:9","resolution": "720p"}}'
借助 Google Omni Flash API 构建 AI 视频工作流
基于多模态提示词与参考素材生成 AI 视频
使用 Google Omni Flash API 通过首尾关键帧生成完整视频
借助 Gemini Omni 1.1 Flash 从快速草稿提升至 4K
Kie AI 平台 Gemini Omni 1.1 Flash API 的核心功能
使用 Gemini Omni 1.1 Flash API 扩展场景
使用 Google Omni Flash API 控制首尾帧
使用 Gemini Omni 更快速地生成 360p 视频草稿
使用 Gemini Omni 1.1 Flash 生成 1080p 和 4K 视频
使用 Gemini Omni 基于参考视频进行生成
通过谷歌 Gemini Omni 1.1 Flash API 掌控电影级运镜
如何在 Kie AI 上使用 Gemini Omni 1.1 Flash API
- 1
第一步 — 在 Kie AI Playground 在线体验 Gemini Omni 1.1 Flash
在编写代码前,您可以先在 Kie AI 的在线 Playground 中探索 Gemini Omni 1.1 Flash。只需通过简单的网页端操作流程,即可轻松尝试提示词、上传参考素材、对比生成结果并测试视频控制功能。 - 2
第二步 — 获取您的 Gemini Omni 1.1 Flash API 密钥
创建 Kie AI 账号,获取您的 Gemini Omni 1.1 Flash API 访问凭证。在同一平台上即可完成从在线测试到开发者集成的无缝切换,无需自行搭建模型基础设施。 - 3
第三步 — 向谷歌 Gemini Omni Flash API 发送提示词与参考素材
将 Google Omni Flash API 接入您的应用,并发送工作流所需的输入数据。根据任务需求,您可以使用文本提示词、图像、参考视频或首尾帧,来引导内容的生成与编辑。 - 4
第 4 步 — 生成 Gemini Omni 视频并将其添加到您的应用中
执行 Gemini Omni 1.1 Flash API 请求,在您的 SaaS 产品、创意平台或自动化媒体工作流中使用生成的视频。在测试创意时可以先快速生成草稿,随后再输出高分辨率视频用于最终成片。