Extensions/PromptModels Studio
ComfyUI Extension

PromptModels Studio

PromptModels Studio-nodos ComfyUI para NVIDIA NIM, Google Gemini y Grok. Zero SDKs externos, solo REST nativo.

By cdanielp·Created 9 months ago·Updated 2 months ago· 28
cdanielp/COMFYUI_PROMPTMODELS
Nodes41
On cloudLocal install
CategoryPrompt Tools, 🧩 Utility
Stars28
Updated2 months ago

Nodes (41)

DivisorDePrompts (10)

One multiline text box, up to ten separate prompt outputs

Prompt Tools
Get Frame by Index

Pull any single frame out of a video batch

🧩 Utility
Get Last Frame

Grab the final image out of a video batch

🧩 Utility
Google AI - Compatibility Checker

Will this LoRA work with that checkpoint?

Google AI/Diagnostic
Google AI - Image Generator (Imagen 4)

Cloud images without the SDKs

Google AI/Image
Google AI - Training Analyzer

A second opinion on your LoRA loss curve

Google AI/Diagnostic
Google AI - Architecture Detector

Point it at a .safetensors and learn what it is

Google AI/Diagnostic
Google AI - Nano Banana (NB2/Pro)

Google's flagship image model, in your graph

Google AI/Image
Google AI - Text Generator

The most flexible node in this pack

Google AI/Text
Google AI - Vision Analyzer

Point Gemini at up to five images, get text back

Google AI/Text
Google AI - Trigger Word Extractor

Stop guessing which token makes your LoRA work

Google AI/Diagnostic
Google AI - Video Generator (Veo 3.1)

Cloud video with native audio

Google AI/Video
Google AI - Video Interpolation

Bridge two frames into a Veo-generated clip

Google AI/Video
Google AI - Video Storyboard

A Veo clip that follows your reference frames

Google AI/Video
Google AI - Workflow Analyzer

Paste someone's JSON, get a plain-English breakdown

Google AI/Diagnostic
Grok Chat (PMS)

Prompt expansion through xAI's Grok models

PromptModels/Grok
Imagen latente Pro

Empty latents with sane presets and a strict mode

Selectores Pro
Dual Prompt List Batch (PMS)

The scene-splitting node for story pipelines

PromptModels/batch
Gemini Chat (PMS)

A text LLM, vision model, and YouTube analyzer in one node

Google AI/Text
Gemini Chat V3 (PMS)

The one to use when you're building fresh

PromptModels/Google
Gemini Text to Speech (PMS)

Five named voices, one REST call

PromptModels/Google
Grok Image Gen (PMS)

Cloud images from xAI, with a built-in anti-crash net

PromptModels/Grok
Grok Speech to Text (PMS)

The transcription half of the voice pipeline

PromptModels/Grok
Grok Text to Speech (PMS)

Put a voice line in your pipeline, tags and all

PromptModels/Grok
Grok Video Gen (PMS)

The node that hands you a URL

PromptModels/Grok
Nano Banana - Imagen IA (PMS)

Nano Banana in ComfyUI, without renting a GPU for it

Google AI/Image
NIMbus Text (PMS)

Chat with NVIDIA's hosted LLMs right inside ComfyUI

PromptModels/NVIDIA (NIMbus)
NIMbus Vision (PMS)

A vision-language model that actually looks at your image

PromptModels/NVIDIA (NIMbus)
Video Batch Concat (PMS)

Stitch scene frames and audio into one timeline

PromptModels/batch
🗑️ PRO Clear Cache

The reset button your PRO Set/Get workflow forgot it needed

GetSetNode_Pro/utils
📤 PRO Get Node

Read back any value you stored with PRO Set

GetSetNode_Pro/utils
📋 PRO List Cache

The debug window into your graph's shared memory

GetSetNode_Pro/utils
Prompt Pro

A structured prompt builder that thinks in scenes, not keywords

Selectores Pro
📦 PRO Set Node

Stash a model, image, or text under a name and read it anywhere

GetSetNode_Pro/utils
📦 PRO Set Node (Named)

The Set node that stops guessing your variable name

GetSetNode_Pro/utils
🧠 PRO Unet Loader GGUF

A model loader that's wider than it looks

GetSetNode_Pro/loaders
🧠 PRO Unet Loader GGUF+

The same loader, with a dtype override and a report card

GetSetNode_Pro/loaders
Selector de imágenes

Pick or batch 12 image+mask pairs without touching a router

Selectores Pro
Selector de Prompts

Twelve prompt slots, one clean output

Selectores Pro
🛡️ Text Prompt Blocker

The guardrail that fails loud on purpose

Text/Security
🔍 Text Prompt Blocker (Preview)

The safe way to tune your blocklist

Text/Security
Readme

PromptModels Studio — ComfyUI Custom Nodes

v3.0.0 · Requiere ComfyUI >= 0.26.0

Nodos de IA para ComfyUI: NVIDIA NIM, Google Gemini y Grok. Sin SDKs externos — solo REST nativo con requests y Pillow.


Nodos activos en v3.0.0

Nuevos — v3 (sin deprecar, 3 nodos)

| Nodo | Categoria | API | Descripcion | |------|-----------|-----|-------------| | PMS_NimbusText | PromptModels/NVIDIA (NIMbus) | NVIDIA NIM | Chat con modelos de texto: Nemotron, DeepSeek V4 | | PMS_NimbusVision | PromptModels/NVIDIA (NIMbus) | NVIDIA NIM | Analisis de imagen multimodal (VL models) | | PMS_GeminiChatV3 | PromptModels/Google | Gemini API | Chat Gemini con thinking budget (Gemini 3+ / 2.5) |

No activos todavia (v3.1.0): PMS_GrokChat, PMS_GrokImageGenV3, PMS_GrokImageEdit, PMS_NanoBananaGen, PMS_NanoBananaEdit — el codigo existe pero estan fuera de get_node_list hasta tener key Grok y billing Gemini.

Legacy — 38 nodos (is_deprecated=True, siguen activos)

Funcionan igual que en v2. Se mantienen para compatibilidad con workflows existentes.

| Modulo | Cantidad | Nodos | |--------|----------|-------| | google_ai | 15 | GoogleAI_TextNode, PMS_GeminiChat, GoogleAI_TextVisionNode, GoogleAI_NanoBananaNode, PMS_NanaBanana, GoogleAI_ImageNode, GoogleAI_VideoGenerator, GoogleAI_VideoInterpolation, GoogleAI_VideoStoryboard, GoogleAI_ModelArchitectureDetector, GoogleAI_TriggerWordExtractor, GoogleAI_WorkflowAnalyzer, GoogleAI_CompatibilityChecker, GoogleAI_LoRATrainingAnalyzer, PMS_GeminiTTS | | grok_ai | 5 | GrokTextNode, PMS_GrokImageGen, PMS_GrokVideoGen, PMS_GrokTTS, PMS_GrokSTT | | getset_pro | 7 | PRO_SetNode, PRO_GetNode, PRO_UnetLoaderGGUF, PRO_SetNodeNamed, PRO_UnetLoaderGGUFAdvanced, PRO_ListCacheNode, PRO_ClearCacheNode | | selectores | 4 | SelectorDeImagenes, SelectorDePrompts, ImagenLatentePro, PromptPro | | batch | 2 | PMS_DualPromptListBatch, PMS_VideoBatchConcat | | frame | 2 | GetLastFrame, GetFrameByIndex | | blocker | 2 | TextPromptBlocker, TextPromptBlockerPreview | | divisor | 1 | DivisorDePrompts | | Total | 38 | |


Instalacion

  1. Copia esta carpeta en ComfyUI/custom_nodes/COMFYUI_PROMPTMODELS/
  2. Crea un archivo .env en la raiz del paquete con tus API keys:
NVIDIA_API_KEY=nvapi-...
GEMINI_API_KEY=AI...
XAI_API_KEY=xai-...
  1. Reinicia ComfyUI.

Las keys tambien se pueden pegar en el input api_key de cada nodo (ver advertencia abajo).


Protege tu API key

Advertencia importante: si pegas una API key directamente en el campo api_key de un nodo, esa key queda expuesta en dos lugares:

  • El JSON del workflow — el archivo .json que guardas o compartes contiene el valor en texto plano.
  • Los metadatos PNG — cuando guardas una imagen desde ComfyUI, el workflow completo (con la key) se embebe en los metadatos del PNG.

Recomendacion: usa siempre el archivo .env o una variable de entorno del sistema (NVIDIA_API_KEY, GEMINI_API_KEY, XAI_API_KEY). Asi el campo api_key del nodo queda vacio y la key nunca viaja en tus archivos.


Variables de entorno

| Variable | Proveedor | |----------|-----------| | NVIDIA_API_KEY | NVIDIA NIM (PMS_NimbusText, PMS_NimbusVision) | | GEMINI_API_KEY | Google Gemini (todos los nodos Google AI) | | XAI_API_KEY | Grok / xAI (todos los nodos Grok) |

Prioridad de resolucion: input del nodo > variable de entorno > .env


Que viene en v3.1.0

  • Nano Banana Gen + Edit — generacion y edicion de imagenes con Gemini (/v1beta/interactions). Requiere cuenta Gemini con billing activo.
  • Grok completo — PMS_GrokChat, PMS_GrokImageGenV3, PMS_GrokImageEdit (codigo listo, activacion pendiente de XAI_API_KEY).
  • Video — nodos de video Veo y Grok en API v3.
  • Voz — TTS/STT actualizados a v3.

Requisitos

  • ComfyUI >= 0.26.0
  • Python >= 3.10
  • requests
  • Pillow