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.
Taskisteğe bağlı
Task type for the model.
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.
Video URListeğe bağlı
URL to the source video file. If provided, the model will use this video as a reference.
Mask Video URListeğe bağlı
URL to the source mask file. If provided, the model will use this mask as a reference.
Mask Image URListeğe bağlı
URL to the guiding mask file. If provided, the model will use this mask as a reference to create masked video. If provided mask video url will be ignored.
Reference Image URLsisteğe bağlı
URLs to source reference image. If provided, the model will use this image as reference.
First Frame URListeğe bağlı
URL to the first frame of the video. If provided, the model will use this frame as a reference.
Last Frame URListeğe bağlı
URL to the last frame of the video. If provided, the model will use this frame as a reference.
Enable Safety Checkeristeğe bağlı
If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked.
Enable Prompt Expansionisteğe bağlı
Whether to enable prompt expansion.
Preprocessisteğe bağlı
Whether to preprocess the input video.
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.
Auto Downsample Min FPSisteğe bağlı
The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences.
Interpolator Modelisteğe bağlı
The model to use for frame interpolation. Options are 'rife' or 'film'.
Transparency Modeisteğe bağlı
The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled.
Return Frames Zipisteğe bağlı
If true, also return a ZIP file containing all generated frames.
