Nodes/comfyui-stillfront/SF VertexAI Imagen 3 Text to Image
ComfyUI Node

SF VertexAI Imagen 3 Text to Image

A ComfyUI node in Stillfront/VertexAI with 12 inputs and 1 output.

By razvanmatei-sf·Created 8 months ago·Updated 6 months ago· 0
SF VertexAI Imagen 3 Text to Image
    • images
    project_id
    locationus-central1
    prompt
    modelimagen-3.0-generate-002
    aspect_ratio1:1
    num_images1
    seed1394699067
    negative_prompt
    safety_filter_levelBLOCK_MEDIUM_AND_ABOVE
    person_generationALLOW_ADULT
    enhance_promptfalse
    output_formatimage/png
    CategoryStillfront/VertexAI

    Inputs (12)

    NameTypeDefaultDescription
    project_idSTRINGGoogle Cloud project ID
    locationSTRINGus-central1Google Cloud region (e.g., us-central1)
    promptSTRINGText description of the image to generate
    modelCOMBOimagen-3.0-generate-002Imagen 3.0 model variant
    aspect_ratioCOMBO1:1Output image aspect ratio
    num_imagesINT11–4Number of images to generate (1-4)
    seedINT13946990670–4294967295Random seed for reproducible results
    negative_promptoptSTRINGWhat to avoid in the generated image (only supported by 001 models)
    safety_filter_leveloptCOMBOBLOCK_MEDIUM_AND_ABOVESafety filter strictness level
    person_generationoptCOMBOALLOW_ADULTPerson generation policy
    enhance_promptoptBOOLEANfalseUse prompt rewriter to enhance the prompt (only 002 model)
    output_formatoptCOMBOimage/pngOutput image format

    Outputs (1)

    NameTypeDescription
    imagesIMAGE