Sign In
home
models
images
videos
posts
articles
bounties
tools
challenges
events
shop

💪 Flexi-Workflow :: Flux & SDXL Variants

33
671
19
Updated: Apr 14, 2025
toolworkflowreduxworkflowssdxlflux.1
Download (95.72 MB)
Verified:
Other
Type
Workflows
Stats
76
0
Reviews
(4)
Published
Apr 13, 2025
Base Model
Flux.1 D
Hash
AutoV2
DF082E9DA4
default creator card background decoration
kaptainkory's Avatar
kaptainkory
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Introduction

💪 This is my attempt at a flexible and extensible workflow framework in both Flux and SDXL variants. Many customizable pathways are possible to create particular recipes 🥣 from the available components, without unnecessary obfuscation (e.g., noodle convolution, stacking nodes over others, etc.) and arguably capable of rendering results of similar quality to more complicated specialized workflows.

The workflow was developed and tested on the following system:

  • Operating system: Linux Mint 21.3 Cinnamon with 62 GB RAM

  • Processor: 11th Gen Intel© Core™ i9-11900 @ 2.50GHz × 8

  • Graphics card: NVIDIA GeForce RTX 3060 with 12 GB VRAM

  • Browser: Google Chrome

Please report bugs 🪲 or errors 🚫, as well as successes 🤞 and requests/suggestions 📝. Post and share your SFW creations!!! I spent a lot of time working on this project (((for no 💰))), so I hope others make good use of it and find it helpful.

New in Version 4

  • Added Gemini AI, facial expression editor, and Thera upscaler.

  • Replaced Hunyuan video with Wan 2.1 video:

    • employs (mostly) native nodes

    • text-to-video, image-to-video (default), and video-to-video (using ControlNet) options

    • ControlNet Fun and LoRA models implemented; VACE not yet available

    • simple upscaling and interpolation

  • Replaced OmniGen with EasyControl 🚧, but the current implementation is experimental and exceeding my available VRAM to even run.

  • MutiGPU loaders now default, except for Wan where they seemed to be a source of instabilities.

  • Overhauled ControlNets + groups:

    • simplified Redux

    • restructured basic ControlNets to allow three different models concurrently

    • regional control that respects different LoRAs

  • Cleaned up and improved workflow:

    • more color-coding of nodes

    • better organization and sorting of bookmarks

    • added global seed node

    • added simple latent operations (between samplers)

    • fixed default masking bug

    • upgraded inpainting crop-and-stitch

    • added model switch, for easier implementation of specialized recipes

Flux

The Flux version 4 is highlighted by Flux Tools 🛠️: Fill (optionally with ACE++), Canny & Depth, and Redux. Basic ControlNets are also available, including regional control, along with two face swap tools (PuLID and ZenID), detailing, relighting, EasyControl 🚧, facial expression editor, and RF inversion. Additional accessories include four captioners (Florence2, JoyCaption2, WD14 Tagger, and SuperPrompt), three background removers (RemBG, RMBG, and Florence2 + SAM2), XY plots, five upscalers (basic, Thera, InvSR, Ultimate SD, and SUPIR), three video generators (DepthFlow, Sonic for talking avatars, and Wan), and stereoscope. A simple interface for Gemini AI is included. Core 🦴 and lite 🪶 editions are also available in the package.

SDXL

The SDXL version 4 includes all of the components of the Flux variant, except for Flux Tools, RF inversion, and EasyControl. Core 🦴 and lite 🪶 editions are also available in the package.

Lightly modified versions of the core 🦴 edition have been confirmed to run the default text-to-image recipe 🥣 on the following models: SD 1.5*, SDXL finetunes: Illustrious, NoobAI, and Pony; SD 3.5; Hunyuan-DiT*; Kolors; PixArt Sigma; and TinyBreaker. [* = may work better w/o --use-sage-attention]

Installation [Flux]

Quick Start

  1. Install or update ComfyUI to the very latest version. Follow your favorite YouTube installation video, if needed.

  2. Install ComfyUI Manager.

  3. Download the following models (or equivalents). Follow the Quickstart Guide to Flux.1, if needed.

  4. Download the FLUX.1-Turbo-Alpha LoRA.

  5. Open the Flux :: Flexi-Workflow in ComfyUI. You may want to start with the lite 🪶 edition, especially if you are new to ComfyUI.

  6. Use the Manager to Install Missing Custom Nodes. It is recommended to install just a few custom node packages at a time until you get through all of them. You may need to set security_level = normal- (notice the dash/minus!) in the config.ini file to download some custom nodes.

  7. Restart ComfyUI.

  8. Load models (01a) and LoRAs (03c) according to your folder structure.

  9. Run the default text-to-image recipe 🥣.

  10. Enjoy your generated image creations! 😎

Navigation & Recipes [Flux]

The workflow is structured for flexibility. With just a few adjustments, it can flip from text-to-image to image-to-image to inpainting or application of Flux Tools 🛠️. Additional unlinked nodes have been included to provide options and ideas for even more adjustments, such as linking in nodes for increasing details. (The workflow does not employ Anything Everywhere, so if a node connection looks empty, it really is empty.)

In the Switchboard, flip the yes|no 🔵 toggles to activate or deactivate groups and the jump arrows ➡️ to quickly move to particular groups for checking and making adjustments to the settings/switches.

🛑 DO NOT RUN THE WORKFLOW WITH ALL SWITCHES FLIPPED TO "YES"! 🛑

There are also bookmarks 🔖 to help you navigate quickly.

In the rgthree settings, it is also recommended to show fast toggles in group headers for muting.

In the Lite Graph section of the settings, enable the fast-zoom shortcut and set the zoom speed to around 1.5–1.75. The workflow was built with a snap to grid size of 20.

Most of the workflow is unpinned 📌, so grab any empty space with your mouse (while pressing the control key) to navigate around. You are welcome to pin 📌 anything to prevent accidentally moving groups or nodes.

Text-to-Image

This is the default recipe 🥣 and should be run first to make sure you have the basics configured correctly.

💪 :: Toggle to "yes" 01a; 02b; 03 all; 04; and 05
03a :: Latent switch = 1 (empty)
03b :: Conditioning switch = 1 (no ControlNets +)
03e :: Denoise = 1; Guidance = 1.2–5; Steps 20–30, or 8–12 w/ Turbo LoRA
05 :: Image switch = 2 (save generated image)

Additional Recipes

Reference the Start Here group to find additional workflow recipes 🥣. For convenience, the package includes several PNG images 🖼️ with embedded workflows.