Negative Promptisteğe bağlı
Negative prompt for video generation.
Match Input Number of Framesisteğe bağlı
If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter.
Number of Framesisteğe bağlı
Number of frames to generate. Must be between 81 to 241 (inclusive).
Match Input Frames Per Secondisteğe bağlı
If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter.
Frames per Secondisteğe bağlı
Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true.
Seedisteğe bağlı
Random seed for reproducibility. If None, a random seed is chosen.
Resolutionisteğe bağlı
Resolution of the generated video.
Aspect Ratioisteğe bağlı
Aspect ratio of the generated video.
Number of Inference Stepsisteğe bağlı
Number of inference steps for sampling. Higher values give better quality but take longer.
Guidance Scaleisteğe bağlı
Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt.
Sampleristeğe bağlı
Sampler to use for video generation.
Shiftisteğe bağlı
Shift parameter for video generation.
Enable Safety Checkeristeğe bağlı
If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked.
Accelerationisteğe bağlı
Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster.
Video Qualityisteğe bağlı
The quality of the generated video.
Video Write Modeisteğe bağlı
The write mode of the generated video.
Number of Interpolated Framesisteğe bağlı
Number of frames to interpolate between the original frames. A value of 0 means no interpolation.
Temporal Downsample Factoristeğe bağlı
Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied.
Enable Auto Downsampleisteğe bağlı
If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.
Return Frames Zipisteğe bağlı
If true, also return a ZIP file containing all generated frames.
