Support for controlnet_mediapipe_face

[Tinaa23]

Hi. Thank you for publishing this amazing work. I was wondering how can we use controlnet_mediapipe_face with animatediff-cli-prompt-travel. Although it is defined in the controlnet_address_table in the generate.py file, when I include and enable it in the json file it doesn't extract face landmarks and this condition is not included in the generation process. Is it because the way I specified it in the config file is incorrect or controlnet_mediapipe_face is not supported at this stage?

"controlnet_mediapipe_face": {
      "enable": true,
      "use_preprocessor":true,
      "guess_mode":false,
      "controlnet_conditioning_scale": 1.0,
      "control_guidance_start": 0.0,
      "control_guidance_end": 1.0,
      "control_scale_list":[0.5,0.4,0.3,0.2,0.1]
    },