Buat task image-to-video Kling
Ubah satu gambar menjadi video Kling melalui CometAPI POST /kling/v1/videos/image2video, dengan pembuatan task async dan pelacakan progres berdasarkan task ID.
Sebelum Anda memanggilnya
- Sediakan satu URL gambar publik atau satu string gambar base64
- Gunakan gambar yang memenuhi persyaratan piksel Kling; thumbnail yang sangat kecil akan ditolak oleh task generation
- Mulailah dengan contoh default
kling-v2-6, lalu pilihmodel_namelain dari enum OpenAPI saat Anda memerlukan track model yang berbeda - Buat request pertama tetap sederhana: satu gambar input, satu prompt, tanpa tail frame, tanpa motion mask
- Gunakan
dynamic_maskssebagai array objek mask-and-trajectory saat Anda memerlukan motion lokal yang terkontrol - Gunakan
sound: offuntuk request pertama tanpa audio yang deterministik pada track model yang mendukung generated sound
Penamaan model
Gunakan model ID video Kling biasa pada endpoint ini. Simpan model ID Omni untuk Omni Video.Alur task
Kirim request image-to-video
task_id yang dikembalikan.Poll task
Simpan hasilnya
Otorisasi
Bearer token authentication. Use your CometAPI key.
Body
Source image URL or base64 image string. Use an image that meets Kling pixel requirements; very small thumbnails are rejected. For base64 input, send the encoded image string as the field value.
Text prompt describing the desired motion. Maximum 500 characters.
Elements to exclude from the video. Maximum 200 characters.
Webhook URL to receive task status updates when the task completes.
Generation mode. std for standard (faster), pro for professional (higher quality).
std, pro Model ID for this image-to-video request. Use kling-v3 for new requests. Use Omni model IDs only with the Omni Video endpoint.
kling-v1, kling-v1-5, kling-v1-6, kling-v2-master, kling-v2-1, kling-v2-1-master, kling-v2-5-turbo, kling-v2-6, kling-v3 Tail-frame reference image as a Base64 string or public URL. Same format requirements as image. Controls the last frame of the generated video.
Prompt adherence strength. Higher values follow the prompt more closely. Range: 0–1.
Output video length in seconds. Use 5 or 10; omit to use 5.
Static brush mask image as a Base64 string or public URL. White areas are frozen in place during video generation. Must match the aspect ratio and resolution of the input image.
Optional motion masks. Each entry contains a mask image and an ordered trajectory list.
Custom task id for your own tracking. Does not replace the system-generated task id but can be used to query tasks. Must be unique per user.
Optional generated-audio switch for models that support video sound. Use on or off, or omit the field for the model default.
on, off