FLUX 3 PE GGUF (T8)

FLUX 3 PE GGUF · T8

English | 简体中文

Local prompt enhancement for ComfyUI, powered by Black Forest Labs' FLUX 3 Image Klein PUP and a Q4_K_M GGUF backend. Turn short requests, reference images and layout boxes into detailed prompts for FLUX 3 workflows.

Models · Runtime downloads · Workflow preview

Features

• Text enhancement, reference-image editing instructions and both layout modes.
• Up to 10 reference images, with explicit image order and locked object boxes.
• STRING output for text encoders, configurable result caching and a maximum of one recovery attempt.
• PE memory release before image generation with keep_loaded=false.

Installation

Requires Windows x64, an NVIDIA GPU, a driver supporting CUDA 13.4, and a recent ComfyUI with the V3 node API. The distributed runtime includes the PE sampling extension.

1. Install FLUX 3 PE GGUF (T8) through ComfyUI Manager when the Registry version is available, or clone into ComfyUI/custom_nodes:

   git clone https://github.com/T8mars/Comfyui-Flux3-PE-GGUF-T8.git ComfyUI-Flux3-PE
   

2. Use your ComfyUI Python to install requirements.txt.

3. Download these files from the model repository into the node folder's models/gguf/:

   | File | Size | |---|---:| | flux3-klein-pup-Q4_K_M.gguf | 5.63 GB | | mmproj-flux3-klein-pup-F16.gguf | 0.92 GB | | manifest.json | Small metadata file |

4. Download flux3-pe-runtime-win-x64-cuda13.4.zip from Releases, extract it into the node folder, and restart ComfyUI. The executable should be at runtime/bin/llama-server.exe.

Model files stay outside Git and the Registry package. Enhancement runs locally; node execution does not upload prompts or reference images.

Usage

1. Add FLUX 3 PE Model (GGUF) and select the Q4_K_M model.
2. Connect it to FLUX 3 Prompt Enhancement and enter a prompt. Connect images in reference order when needed.
3. Connect enhanced_prompt to a text encoder or ComfyUI's Preview as Text. details_json reports timing, caching and recovery.

Leave keep_loaded=false when the next step generates an image. Disable use_cache to force a new enhancement.

Layout input uses normalized [y_min, x_min, y_max, x_max] coordinates:

[{"id":"balloon","desc":"a red balloon","bbox":[0.1,0.1,0.6,0.4]}]

For reference-image layouts, use from="ref_image_0", src_bbox and tgt_bbox. New objects use from="target" and src_bbox=null; removed objects use tgt_bbox=null.

Example workflows

Drag a JSON file from examples into ComfyUI:

• Text enhancement
• Layout enhancement
• PE → FLUX 3 image generation
• Two-reference editing instructions

To copy all four workflows and their reference images into your installation, run from the node folder:

& .\scripts\install_comfy.ps1 -ComfyUI 'C:\path\to\ComfyUI'

The image-generation example additionally requires FLUX 3 diffusion weights, its Qwen3-VL text encoder and FLUX.2 VAE. These are separate downloads.

Validation and development

The PE core passed 40 structural/text-preservation cases, seven real canvas executions, workflow save/reopen checks and PNG workflow restoration. One Chinese editing case used the bounded recovery path. These checks do not guarantee semantic correctness for every prompt.

Development, runtime build and benchmark notes

T8star links

Bilibili · YouTube · API · Free gallery

Online AI apps · ComfyUI bundle · Hugging Face

Credits and license

Node integration: T8star. PUP weights and reference code: Black Forest Labs, Apache-2.0. Runtime: llama.cpp, MIT, with the included sampling patch. CUDA libraries retain NVIDIA's license terms. See LICENSE, NOTICE and licenses.