Nodes/VRGameDevGirl Video Enhancement Nodes/VRGDG_PromptSplitterForFMML
ComfyUI Node

VRGDG_PromptSplitterForFMML

The scene-picker splitter that defaults to an array

By vrgamegirl19·Created about a year ago·Updated about 7 hours ago· 718
VRGDG_PromptSplitterForFMML
    • text_output_1
    • text_output_2
    • text_output_3
    • text_output_4
    • text_output_5
    • text_output_6
    • text_output_7
    • text_output_8
    • text_output_9
    • text_output_10
    • text_output_11
    • text_output_12
    • text_output_13
    • text_output_14
    • text_output_15
    • text_output_16
    json_string[]
    index0

    VRGDG_PromptSplitterForFMML is another member of the pack's index-based splitter family, and apart from two small differences it's a clone of VRGDG_PromptSplitterForFL: JSON in, an index to pick the scene, sixteen text outputs out.

    The two differences are worth knowing because they'll affect what you paste in:

    • Its json_string input defaults to [] - an empty array - rather than {} (an empty object). The "FMML" variant expects a JSON array of scene entries, one element per index, instead of a keyed object.
    • It's tied to a different section of the pack's workflow than the FL version. The acronyms aren't documented anywhere in the README, so don't burn time trying to decode them - treat "FL", "FMML", and "Manual" as workflow-internal labels, and use whichever one the workflow you loaded references.

    How it works

    Two required inputs:

    • json_string - a JSON array of scene entries as text. Element 0 is scene 0, element 1 is scene 1, and so on.
    • index - which scene to pull, 0 to 10000. Zero-based, so the first scene is index: 0.

    Outputs: text_output_1 through text_output_16, all STRING - the selected scene's entry unpacked into sixteen slots for whatever the workflow section consumes. Which slot means what isn't documented beyond the ports themselves; in practice you wire them into the video-generation chain in the order the workflow expects.

    Where it sits

    Like its siblings, this is loop plumbing: a stepper advances the index, the splitter pulls that scene's parameters, and the video node renders one chunk per run. The array-based format suggests it reads the output of a node that writes scenes as a flat list rather than a keyed map - the pack's LLM node can emit either shape depending on how it's asked.

    Installing it

    Part of the pack:

    cd ComfyUI/custom_nodes
    git clone https://github.com/vrgamegirl19/comfyui-vrgamedevgirl
    

    restart, or ComfyUI Manager → search vrgamedev. No models, no heavy deps.

    The honest take

    If your prompt map is an object, use the object-based splitter; if it's an array, use this one. That's genuinely the whole decision - the index-picking behavior is otherwise identical. When in doubt, match the variant to the workflow that shipped with it and you won't go wrong.

    CategoryVRGDG

    Inputs (2)

    NameTypeDefaultDescription
    json_stringSTRING[]
    indexINT00–10000

    Outputs (16)

    NameTypeDescription
    text_output_1STRING
    text_output_2STRING
    text_output_3STRING
    text_output_4STRING
    text_output_5STRING
    text_output_6STRING
    text_output_7STRING
    text_output_8STRING
    text_output_9STRING
    text_output_10STRING
    text_output_11STRING
    text_output_12STRING
    text_output_13STRING
    text_output_14STRING
    text_output_15STRING
    text_output_16STRING