Extensions/ComfyUI Assistant Node
ComfyUI Extension

ComfyUI Assistant Node

A custom ComfyUI node that integrates with the OpenAI Assistants API.

By pvlprk·Created about a year ago·Updated 8 months ago· 1
pvlprk/comfyui-pvl-api-nodes
Nodes84
On cloudLocal install
CategoryPVL/Converters, EasyUse/Logic
Stars1
Updated8 months ago

Nodes (84)

PVL Any To String

Turn a bool, an int, and a float into one tidy string

PVL/Converters
PVL Batch Any

Images, latents, numbers, lists

EasyUse/Logic
PVL BooleanLogic

A two-input AND/OR gate for your workflow, that's the whole node

PVL
PVL Call OpenAI Assistant

The node this whole pack is named after

PVL_tools
PVL Check If Connected

One wildcard input, a passthrough and a has_value flag

PVL_tools
PVL Color Match

Steal the color grade from one image and slap it on another

PVL_tools/image
PVL ComfyDeploy API Caller

A very specific ComfyDeploy deployment, driven from your graph

PVL_tools
PVL ComfyDeploy Avatar PulID API

Queue an avatar-generation deployment and pull the result back

PVL/API
PVL ComfyDeploy Universal

Name your own inputs

PVL/API
PVL Compare

The two-second comparison node that unblocks whole workflow branches

PVL/Logic
PVL Crop to Aspect Ratio

The one node that does exactly one thing, and does it locally

PVL_tools
PVL Crop To Mask

Crop a subject out of a mask's bounding box, padding included

PVL Nodes/Image
PVL Edge Extend

March the alpha outward

image/alpha
PVL Depth Anything V2 (fal.ai)

A depth map from the cloud, zero preprocessor setup

PVL_tools
PVL Segment (fal.ai)

Describe an object, get its mask back — no local GPU needed

PVL_tools_FAL
PVL Segment X5 (fal.ai)

Five images, five text prompts, one parallel segmentation call

PVL_tools_FAL
PVL Flux.2 Camera Control (fal.ai)

Orbit a camera around a single image with Flux.2

PVL_tools_FAL
PVL Flux.2 Dev (fal.ai)

Flux 2 Dev in ComfyUI without the 24 GB of VRAM

PVL_tools_FAL
PVL Flux.2 Flex (fal.ai)

The faster, cheaper way to use Flux 2 without local VRAM

PVL_tools_FAL
PVL Flux.2 Pro (fal.ai)

The flagship, with none of the local install

PVL_tools_FAL
PVL FLUX DEV (fal.ai)

The 'just generate' node

PVL_tools_FAL
PVL Flux Dev Inpaint (fal.ai)

Mask-based Flux inpainting in the cloud, the honest way

PVL_tools_FAL
PVL Flux Dev Pulid Avatar (fal.ai)

One photo in, stylized avatars out — PuLID identity, zero local setup

PVL_tools_FAL
PVL FLUX General (fal.ai)

NAG guidance, shifts, and reference images

PVL_tools_FAL
PVL FluxPro Fill (fal.ai)

Inpaint the masked region with Flux Pro Fill, all in the cloud

PVL_tools
PVL FluxPro1.1 Ultra (fal.ai)

Flux Pro 1.1 Ultra with parallel requests and per-item retries built in

PVL_tools
PVL Flux PuLID (fal.ai)

Put a face on a Flux image without installing InsightFace

PVL/FAL
PVL FLUX DEV LORA (fal.ai)

Run your trained Flux LoRAs on fal — no local model, no VRAM squeeze

PVL_tools_FAL
PVL Flux Lora PulID (fal.ai)

Flux, a face, and a LoRA — all from the same cloud call

PVL_tools_FAL
PVL Kontext Dev (fal.ai)

Change the prompt, keep the subject

PVL_tools
PVL Kontext Dev Inpaint (fal.ai)

Kontext editing, masked and LoRA-loaded, no local weights

PVL_tools_FAL
PVL Kontext Dev LoRA (fal.ai)

Kontext editing with your LoRA on top — style and subject in one edit

PVL_tools
PVL KONTEXT MAX MULTI (fal.ai)

Merge two or more images with Kontext Max — one instruction, up to four references

PVL_tools_FAL
PVL Kontext Max Single (fal.ai)

The flagship editor, wrapped

PVL_tools_FAL
PVL Kontext Pro (fal.ai)

Kontext Pro, the API-only editor, from inside ComfyUI

PVL_tools
PVL_fal_LumaPhoton_FlashReframe_API

The fast, cheap reframe variant when you're iterating on compositions

PVL_tools
PVL LumaPhoton Reframe (fal.ai)

Repaint your photo into a new aspect ratio with Luma Photon

PVL_tools
PVL Moondream3 Segmentation (fal.ai)

Tell it what to find, get a mask back — no GPU, no model download

PVL_tools
PVL FAL Nano-Banana Edit

Nano Banana editing without renting a 24GB card

PVL_tools
PVL QwenImage txt2img (fal.ai)

Qwen-Image's 20B, rented by the click

PVL_tools_FAL
PVL Remove Background V2 (fal.ai)

BiRefNet cutouts on demand, with the hard cases in mind

PVL_tools
PVL Sam3 Segmentation (fal.ai)

Name an object, get a SAM-3 mask — the heavyweight, hosted

PVL_tools
PVL SeeDream 4.5 (fal.ai)

ByteDance's SeeDream 4.5, without the ByteDance account

PVL_tools_FAL
FAL SeeDream4 Edit (fal.ai)

SeeDream 4 image editing, via fal and inside your graph

PVL_tools
PVL Gemini Api

Batch prompts, retries, and one text output

PVL/LLM
PVL Gemini API (Avatar Special)

The Gemini node built for avatar batch work — with an OpenAI escape hatch

PVL/LLM
PVL Gemini Api Multi

Gemini, six images at a time — the multimodal variant

PVL/LLM
PVL Gemini 2.5 Segmentation

Ask Gemini 2.5 for a mask, not a caption

image/segmentation
PVL Gemini with fallback Api

Gemini first, GPT as the safety net — a text node that survives outages

PVL/LLM
PVL Gemini with fallback Multi

Six images, two providers, one text output

PVL/LLM
PVL Get Image Size

The node that answers 'what size is my image, actually?'

PVL_tools/image
PVL Google NanoBanana API

Nano Banana straight from Google — with a fal.ai parachute

PVL/Google
PVL Google Nano-Banana API mandatory IMG

Nano Banana for edits, where the image isn't optional

PVL/Google
PVL Google NanoBanana API Multi

Nano Banana with up to eight reference images

PVL/Google
PVL Google NanoBanana PRO Multi API

The flagship, multi-image, with Google Search even

PVL/API
PVL Image Batch to Image List

Un-batch your images so list-expecting nodes stop fighting you

PVL/Utils/Image
PVL Image Composite

Paste one image onto another — batch-smart, mask-aware

pvl/image manipulation
PVL Image List to Image Batch

Turn a pile of images into one batch (and back again)

PVL/Utils/Image
PVL Image Resize

The resize node that respects your latent's multiples

PVL_tools
PVL Image Stitch

Stitch up to eight images into one canvas, grid or guillotine

image/compose
PVL Image Translation Offset Detector

Measure how far a frame drifted, down to sub-pixels

image/alignment
PVL Math

Do real math inside your graph, not on a calculator

essentials_mb/utilities
PVL Math Condition

Math that picks its own branch

essentials_mb/utilities
PVL NoneOutputNode

A pass-through you can switch off mid-workflow

utility
PVL Padding

Add white space to an image, one side at a time

PVL/utility
PVL Qwen Image Edit Inpaint (fal.ai)

Qwen editing, but with a mask so it leaves the rest alone

PVL_tools
PVL Qwen Image Edit Multi (fal.ai)

Qwen editing with six reference images and twelve parallel tries

PVL_tools
PVL Save Or Not

Save images, but only when you mean it

PVL_tools
PVL Seg Florence2 (fal.ai)

Segment anything by describing it — in the cloud, no GPU needed

PVL_tools_FAL
PVL Split String

One string in, up to six strings out

PVL_Utils
PVL Stitch 2 Size

A contact sheet that exactly fills the frame

PVL/Image
PVL String Concat x3

Glue three strings together, exactly as written

🧩 PVL/Strings
PVL String Concat x8

Eight strings in, one string out, zero surprises

🧩 PVL/Strings
PVL String List To String

Join a list of strings back into one

PVL/Utils/Text
PVL String To Number

When a string of digits needs to be a real number

PVL_Utils
PVL String To String List

Turn one string into a list, without the manual labour

PVL/Utils/Text
PVL StylePicker

Sixteen art styles behind one dropdown

PVL/Style
PVL Switch

Pick a branch and skip all the wasted work

🟣PVL/utility
PVL Switch Huge

A ten-way switch that only runs the case you picked

PVL_tools
PVL Switch x10

The ten-way switch, again — they ship both, and that's fine

PVL_tools
PVL Switch x15

Lazy branching that only runs what you pick

PVL_tools
PVL Switch x5

The little lazy switch for when five options is plenty

PVL_tools
PVL Text Overlay

Stamp words on your images without leaving ComfyUI

⚙️PVL Nodes/Text
PVL Txt

A no-frills text box that plays nice with dynamic prompts

PVL
Readme

ComfyUI Assistant Node

A custom ComfyUI node that integrates with the OpenAI Assistants API.

Features

  • Call OpenAI Assistant from within ComfyUI
  • Supports dynamic model selection
  • Input fields for API key, assistant ID, seed, and prompt text

Installation

Clone or download this repo into your ComfyUI/custom_nodes/ directory:

git clone https://github.com/pvlprk/comfyui-pvl-api-nodes