Image To Video Endpoint

Generate a video from an image using various AI models. Creates a container scene with the generated video.

Supports multiple models:

• Seedance 1.0 Pro Fast (image-to-video)
• Seedance 1.5 Pro (image-to-video)
• Kling 2.5 Turbo Standard (image-to-video)
• Kling 2.6 Pro (image-to-video, supports native audio)
• Kling O1 (image-to-video)
• LTX Video 2.0 Fast (image-to-video, supports native audio)
• Sora 2 (image-to-video, supports native audio)
• Veo 3.1 Fast (image-to-video, supports native audio)
• Wan 2.6 (image-to-video)

Args: request: JSON body containing: - project_id (str, required): Project ID to add the video to - prompt (str, required): Text prompt describing the video - image_url (str, required): URL of the image to use as first frame - model (str, optional): Model to use. Default: "seedance" - duration (str, optional): Duration in seconds (model-specific). Default: "5" - aspect_ratio (str, optional): Aspect ratio (model-specific) - resolution (str, optional): Video resolution (model-specific) - fps (str, optional): Frames per second (LTX Video 2.0 only) - generate_audio (bool, optional): Whether to generate audio - add_audio (bool, optional): Whether to add audio. Default: False - camera_fixed (bool, optional): Fix camera position (Seedance only) - seed (int, optional): Random seed for reproducibility - enable_safety_checker (bool, optional): Enable safety checker - negative_prompt (str, optional): Negative prompt (Kling/Wan) - cfg_scale (float, optional): CFG scale 0.0-1.0 (Kling) - enable_prompt_expansion (bool, optional): Enable prompt expansion (Wan) - multi_shots (bool, optional): Enable multi-shot segmentation (Wan) - audio_url (str, optional): Background audio URL (Wan) - max_retries (int, optional): Max retry attempts. Default: 3 - initial_delay (float, optional): Initial backoff delay. Default: 1.0

Returns: Success response with scene and video data