Nodes/ComfyUI_Adforge/Vertex Veo Video with Reference
ComfyUI Node

Vertex Veo Video with Reference

Video with Reference Generate videos using a reference image for style guidance with Google's Veo. Inputs: prompt: The text prompt used to guide video generation. reference_image: The image to use as a reference for content or style. Outputs: output_videos: A list of generated videos (VIDEO type). output_video_path_list: A list of local paths to the generated videos (when output_format=local_file) Configuration: aspect_ratio: Optional. Specifies the aspect ratio of generated videos. duration_seconds: Required. The length in seconds of video files that you want to generate. enhance_prompt: Optional. Use Gemini to enhance your prompts. generate_audio: Generate audio for the video. person_generation: Optional. The safety setting that controls whether people or face generation is allowed. resolution: Optional. Veo 3 models only. The resolution of the generated video. seed: Optional. A number to request to make generated videos deterministic. Adding a seed number with your request without changing other parameters will cause the model to produce the same videos. output_gcs_uri: GCS URI where the generated videos will be stored, in the format 'gs://BUCKET_NAME/SUBDIRECTORY'. model: The Veo model to use for video generation. fps: Optional. Frames per second for the generated video. number_of_videos: Optional. Number of video variations to generate. mime_type: Mime type of the input image or video, e.g., 'image/png' or 'video/mp4'.

By Creditas-labs·Created 9 months ago·Updated 9 months ago· 1
Vertex Veo Video with Reference
  • reference_image
  • videos
  • video_path_list
prompt
reference_image_gcs_uri
reference_typeASSET
negative_prompt
output_gcs_uriNone/videos/video-with-reference-20260720-202149.mp4
modelveo-3.1-generate-preview
aspect_ratio16:9
mime_typeimage/png
duration_seconds8
resolution1080p
fps24
number_of_videos1
enhance_prompttrue
generate_audiofalse
person_generationallow_adult
seed0
CategoryAdForge/Video Generation

Inputs (17)

NameTypeDefaultDescription
promptSTRINGThe text prompt used to guide video generation.
reference_imageoptIMAGEThe image to use as a reference for content or style.
reference_image_gcs_urioptSTRINGNo documentation available
reference_typeoptCOMBOASSETAsset image: You provide up to three images of a single person, character, or product. Veo preserves the subject's appearance in the output video. Style image: You provide a single style image. Veo applies the style from your uploaded image in the output video. This feature is only supported by veo-2.0-generate-exp in Preview.
negative_promptoptSTRINGOptional. A text string that describes anything you want to discourage the model from generating.
output_gcs_urioptSTRINGNone/videos/video-with-reference-20260720-202149.mp4GCS URI where the generated videos will be stored, in the format 'gs://BUCKET_NAME/SUBDIRECTORY'.
modeloptCOMBOveo-3.1-generate-previewThe Veo model to use for video generation.
aspect_ratiooptCOMBO16:9Optional. Specifies the aspect ratio of generated videos.
mime_typeoptCOMBOimage/pngNo documentation available
duration_secondsoptINT81–10Required. The length in seconds of video files that you want to generate.
resolutionoptCOMBO1080pOptional. Veo 3 models only. The resolution of the generated video.
fpsoptINT241–60Optional. Frames per second for the generated video.
number_of_videosoptINT11–4Optional. Number of video variations to generate.
enhance_promptoptBOOLEANtrueOptional. Use Gemini to enhance your prompts.
generate_audiooptBOOLEANfalseGenerate audio for the video.
person_generationoptCOMBOallow_adultOptional. The safety setting that controls whether people or face generation is allowed.
seedoptINT00–2147483647Optional. A number to request to make generated videos deterministic. Adding a seed number with your request without changing other parameters will cause the model to produce the same videos.

Outputs (2)

NameTypeDescription
videosVIDEOA list of generated videos (VIDEO type).
video_path_listSTRINGA list of local paths to the generated videos (when output_format=local_file)