sat/configs/inference.yaml

args:
  image2video: False # True for image2video, False for text2video
  latent_channels: 16
  mode: inference
  load: "{your CogVideoX SAT folder}/transformer" # This is for Full model without lora adapter
  # load: "{your lora folder} such as zRzRzRzRzRzRzR/lora-disney-08-20-13-28" # This is for Full model without lora adapter
  batch_size: 1
  input_type: txt
  input_file: configs/test.txt
  sampling_image_size: [480, 720]
  sampling_num_frames: 13  # Must be 13, 11 or 9
  sampling_fps: 8
#  fp16: True # For CogVideoX-2B
  bf16: True # For CogVideoX-5B and CoGVideoX-5B-I2V
  output_dir: outputs/
  force_inference: True