Node packVérifiéExterne

ComfyUI-FL-PixelGen

FL PixelGen - Pixel-space diffusion text-to-image generation and LoRA training nodes for ComfyUI

Sourcegithub.com/filliptm/ComfyUI-FL-PixelGen

Mainteneur@filliptmUnratedClasse

Profil du package

Statut: Vérifié
Éditeur: @filliptm
Source: GitHub
Étoiles: 13

LIREMOI

FL PixelGen

Pixel-space diffusion text-to-image generation and LoRA training nodes for ComfyUI, powered by PixelGen. Generate high-quality images directly in pixel space using a JiT transformer denoiser with Qwen3 text conditioning and flow matching sampling — entirely within ComfyUI's node graph.

PixelGen ComfyUI Patreon

PixelGen Preview

Features

Pixel-Space Diffusion — Generates images directly in pixel space, no VAE decoding needed
Live Sampling Preview — See the image form step-by-step during generation
REPA LoRA Training — 4-component loss (flow matching + cosine alignment + LPIPS + DINO) with noise gating
Real-Time Training UI — Live loss chart, progress bar, validation samples, and lightbox preview via WebSocket widget
Qwen3 Text Encoder — Uses Qwen3-1.7B for text conditioning, auto-downloaded from HuggingFace
Auto Model Download — Denoiser and text encoder models download automatically from HuggingFace on first use

Nodes

Node	Category	Description
FL PixelGen Model Loader	Loaders	Load the PixelGen denoiser model from checkpoint
FL PixelGen Text Encoder Loader	Loaders	Load a Qwen3 text encoder for conditioning
FL PixelGen Generate	Generation	Generate images from text using pixel-space diffusion
FL PixelGen LoRA Loader	Loaders	Load and apply a trained LoRA adapter for inference
FL PixelGen Training Config	Training	Configure LoRA training hyperparameters and REPA loss weights
FL PixelGen Train	Training	Run REPA LoRA training with real-time progress widget

Installation

Manual

cd ComfyUI/custom_nodes
git clone https://github.com/filliptm/ComfyUI-FL-PixelGen.git
cd ComfyUI-FL-PixelGen
pip install -r requirements.txt

The training widget JS is included in js/ and requires no build step.

Quick Start

Inference Pipeline

Load Model — Add FL PixelGen Model Loader and select PixelGen-XXL-T2I
Load Text Encoder — Add FL PixelGen Text Encoder Loader and select a Qwen3 variant
Generate — Connect both to FL PixelGen Generate, enter a prompt, and execute

Training Pipeline

Load Model + Text Encoder — Same loader nodes as inference
Configure — Set LoRA rank, learning rate, epochs, and REPA loss weights in FL PixelGen Training Config
Train — Connect model, text_encoder, and config to FL PixelGen Train with your image directory
Validate — Set a validation prompt to see sample outputs during training

Using Trained LoRAs

Connect a trained LoRA checkpoint to FL PixelGen LoRA Loader between the model loader and generate nodes. Adjust strength to control the effect.

Node Details

FL PixelGen Model Loader

Loads the PixelGen denoiser from a local checkpoint or HuggingFace.

Input	Type	Default	Notes
model_name	Dropdown	`PixelGen-XXL-T2I`	Auto-downloads from HF
device	Dropdown	`cuda`	`cuda` / `cpu`
dtype	Dropdown	`bfloat16`	`bfloat16` / `float32`
force_reload	BOOLEAN	`False`	Bypass model cache