Negative Promptisteğe bağlı
Negative prompt for generation
Lorasisteğe bağlı
LoRA weights to use for generation
Resolutionisteğe bağlı
Resolution of the generated video.
Aspect Ratioisteğe bağlı
The aspect ratio of the video.
Seedisteğe bağlı
Random seed for generation
Number of Framesisteğe bağlı
The number of frames in the video.
Number of Inference Stepsisteğe bağlı
Number of inference steps during the first pass.
Second Pass Number of Inference Stepsisteğe bağlı
Number of inference steps during the second pass.
Second Pass Skip Initial Stepsisteğe bağlı
The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes.
Frame Rateisteğe bağlı
The frame rate of the video.
Expand Promptisteğe bağlı
Whether to expand the prompt using a language model.
Reverse Videoisteğe bağlı
Whether to reverse the video.
Enable Safety Checkeristeğe bağlı
Whether to enable the safety checker. Disabling it requires account authorization; unauthorized requests are always checked.
Enable Detail Passisteğe bağlı
Whether to use a detail pass. If True, the model will perform a second pass to refine the video and enhance details. This incurs a 2.0x cost multiplier on the base price.
Temporal AdaIN Factoristeğe bağlı
The factor for adaptive instance normalization (AdaIN) applied to generated video chunks after the first. This can help deal with a gradual increase in saturation/contrast in the generated video by normalizing the color distribution across the video. A high value will ensure the color distribution is more consistent across the video, while a low value will allow for more variation in color distribution.
Tone Map Compression Ratioisteğe bağlı
The compression ratio for tone mapping. This is used to compress the dynamic range of the video to improve visual quality. A value of 0.0 means no compression, while a value of 1.0 means maximum compression.
Constant Rate Factoristeğe bağlı
The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality.
