FLUX Redux ACE Face Swap
Create consistent, natural identity swaps with advanced reference image control.
AI model workflow
FLUX ComfyUI Workflows
Generate images from text, edit photos, and create character variations with FLUX in ComfyUI. Choose FLUX.1 or FLUX.2 for generation and reference edits, or FLUX Fill for inpainting and outpainting. Run them on RunComfy Cloud, download workflow JSON, or deploy supported workflows as APIs.
47 workflows
Featured workflow
Flux 2 Dev | Photoreal Text-to-Image Generator
The workflows
47 FLUX ComfyUI Workflows
Compare FLUX ComfyUI examples by model version, image inputs, and finished result. Open a workflow for its instructions, sample outputs, and compatible model files. Run it on RunComfy Cloud, download the workflow JSON, or deploy supported workflows as APIs.
FLUX.2 Klein 9B KV Image Edit
Prompt-based image edits that keep structure and identity intact.
FLUX.2 Dev LoRA Inference
Run your AI Toolkit-trained FLUX.2 Dev LoRA in ComfyUI with training-matched behavior using a single RunComfy RC custom node.
FLUX Klein Face Swap
Swap faces perfectly. Natural, lifelike, and fast AI-powered editing.
FLUX.2 Dev Text-to-Image
Next-level image realism with advanced generation control power
FLUX Fill Inpaint & Outpaint
Official Flux Tools - Flux Fill for Inpainting and Outpainting
FLUX Krea Dev Text-to-Image
The best open-source FLUX model! Absolutely incredible natural results.
FLUX Consistent Characters (Input Image)
Create consistent characters and ensure they look uniform using your images.
FLUX Kontext PuLID Characters
Create consistent characters using FLUX Kontext with a single face reference image.
FLUX Kontext Dev Image Editing
Kontext Dev = Controllable + All Graphic Design Needs in One Tool
FLUX RealismLoRA
Blend FLUX-1 model with FLUX-RealismLoRA for photorealistic AI images
FLUX.2 Klein Inpaint, Outpaint & Remove
Flawless editing. Remove, fill, and extend any image fast.
FLUX Image-to-Image
Merge visuals and prompts for stunning, enhanced results.
FLUX 32K Upscaler
Flux Upscaler – Achieve 4k, 8k, 16k, and Ultimate 32k Resolution!
FLUX PuLID Face Swap
Take your face swapping projects to new heights with Flux PuLID.
FLUX Dev ControlNet
Controlled FLUX Dev image generation with Pose, Depth, Canny, and ReColor
FLUX Inpainting
Effortlessly fill, remove, and refine images, seamlessly integrating new content.
FLUX.2 Klein 4B & 9B Image Generation
Blazing-fast visual creation with unified editing control.
PuLID FLUX II Characters
Generate images with precise character control while preserving artistic style.
FLUX TTP 4K Face Restore
Repair distorted faces and upscale images to 4K resolution.
FLUX LoRA Training
Guide you through the entire process of training FLUX LoRA models using your custom datasets.
FLUX Kontext Turnaround Sheet LoRA
Generate 5-pose character turnaround sheets from single image
FLUX ControlNet Depth-V3 & Canny-V3
Achieve better control with FLUX-ControlNet-Depth & FLUX-ControlNet-Canny for FLUX.1 [dev].
FLUX UltraRealistic LoRA V2
Create stunningly lifelike image with Flux UltraRealistic LoRA V2
FLUX Redux Variation & Restyling
Official Flux Tools - Flux Redux for Image Variation and Restyling
FLUX Consistent Characters (Input Text)
Create consistent characters and ensure they look uniform by inputting text.
FLUX.2 Klein 9B LoRA Inference
Generate training-matched FLUX.2 Klein 9B LoRA outputs in ComfyUI through AI Toolkit's pipeline-aligned inference nodes.
FLUX ControlNet Inpainting
Enhance realism by using ControlNet to guide FLUX.1-dev.
FLUX Kontext Style Transfer LoRA
Mix 13 art styles instantly or plug in custom LoRAs!
FLUX.1 Dev LoRA Inference
Run your AI Toolkit-trained FLUX.1 Dev LoRA in ComfyUI with training-matched behavior using a single RCFluxDev custom node.
FLUX Kontext 360° LoRA
Generate immersive 360-style images with depth and spatial control.
FLUX Text-to-Image
A new image generation model developed by Black Forest Labs
32 of 47 workflows shown
About FLUX
What can FLUX do in ComfyUI?
FLUX in ComfyUI supports text-to-image generation, image-to-image editing, and masked edits through different model variants. Change a background, place an object in a scene, create character variations, or explore a new visual style with a workflow designed for that result.
The FLUX family offers different starting points. FLUX.1 Dev supports text-to-image generation and compatible LoRAs; FLUX.2 options cover generation and reference-based editing. Kontext focuses on instruction edits, while Fill is designed for masked edits and canvas extension.
More specialized results depend on the setup around the model. Consistent-character, face-swap, restoration, and structure-guided examples use dedicated references, adapters, or processing steps. Choose by the result and input you need, then open the matching workflow for its model requirements and instructions.
References and model resources: Black Forest Labs FLUX.2 overview, Black Forest Labs FLUX GitHub, ComfyUI GitHub, Explore FLUX models on Hugging Face, Explore FLUX models on Civitai.
Capabilities
Explore FLUX capabilities in ComfyUI
Start with text, an existing photo, or a structural reference. These examples show the main ways to generate and edit images with FLUX in ComfyUI.
Text-to-image generation
Create an image from a written prompt, from a portrait to an imagined scene.
Image-to-image editing
Describe changes to an existing image, using a reference to guide what stays and what changes.
Structure-guided generation
Guide pose, depth, edges, or color with a compatible FLUX ControlNet setup.
Inpainting and outpainting
Edit a masked area or extend an image beyond its original borders with FLUX Fill.
FLUX models on RunComfy
Use FLUX in ComfyUI without local setup
Open a prepared FLUX setup on RunComfy Cloud, then change prompts, images, and settings in ComfyUI. Choose GPU memory for the model and image size you need. Downloading the JSON gives you the workflow structure; running it locally still requires its model files and dependencies.
Run a FLUX workflow nowEditable image controls
Adjust prompts, source images, masks, and settings exposed by your selected FLUX example.
Model and LoRA storage
Bring compatible checkpoints, LoRAs, and control weights into your cloud workspace for reuse.
Prepared dependencies
Start from the example's configured model and node setup, then customize it in ComfyUI.
Cloud GPU options
Match GPU memory to your FLUX model, image resolution, and any additional processing stages.
Applications
What you can make with FLUX
Find an example for the image you want to make, from face edits and object placement to character sheets and restored photos.
Object Placement
Place a product or object reference in a target scene, guided by its scale and surroundings.
Consistent Character Images
Reuse an image reference to create variations of the same character across scenes.
Character Turnaround Sheets
Create front, side, and back-style reference views from a character image.
Photo Restoration
Repair facial detail and increase image resolution with a dedicated restoration pipeline.
Photorealistic Images
Use a compatible realism LoRA to explore photographic lighting, textures, and detail.
Frequently asked questions
FLUX in ComfyUI: FAQ
Choose a FLUX version, understand reference and LoRA options, and decide whether to run in the cloud or download for local ComfyUI.
Which FLUX model should I use?
Choose by your starting point. FLUX.1 Dev is an option for prompt-based images, while FLUX.2 Dev covers another generation path. Use a dedicated FLUX.2 Klein image-editing example when you have a source photo to change. Kontext and Fill serve different editing needs; the selected workflow must match the model and inputs you want to use.
How much VRAM do I need to run FLUX in ComfyUI?
There is no single VRAM requirement for all FLUX models. Model size and format, image resolution, and additional controls all affect memory use. Check the requirements of the specific workflow before downloading its files. RunComfy Cloud is an alternative when your local GPU cannot support that setup.
Should I use FLUX Kontext or FLUX Fill for image editing?
Use Kontext for changes described with text and image references. Use FLUX Fill when you need to edit a masked region or extend the canvas. They solve different editing problems, so choose based on whether you want to guide a whole-image change or target a specific area.
How do I keep a character consistent with FLUX?
Choose a reference-based character workflow when you want variations of a recognizable subject. More specialized options use identity adapters or a compatible character LoRA. Results still need review: keeping a face recognizable is different from preserving every detail of a pose, outfit, or background.
How do I use LoRA or ControlNet in a FLUX ComfyUI workflow?
Use a FLUX LoRA example for a trained visual look, or a FLUX ControlNet example for structural guidance such as pose, depth, or edges. The base model and add-on must target the same FLUX version. To train your own LoRA, choose FLUX.1, FLUX.2, FLUX.2 Klein 4B, or FLUX.2 Klein 9B in RunComfy Trainer.
Where can I download a FLUX ComfyUI workflow JSON?
Use the Download JSON button beside a workflow's Run now button, or download from its detail page. Open that file in ComfyUI to load the workflow. The JSON does not include the model weights or custom nodes, so follow the linked detail page's requirements for a local run.
What do I need for a local FLUX ComfyUI install?
You need ComfyUI plus the model files and any custom nodes required by your chosen example. Those requirements differ across FLUX.1, FLUX.2, and specialized editing setups. Follow the detail page's setup instructions, or use Run now for a prepared cloud environment.
Related resources
More ways to use FLUX
Train a LoRA with a supported FLUX base model, or use FLUX models directly when you do not need a full ComfyUI workflow.
Train a FLUX.1 LoRA
Train a FLUX.1 Dev LoRA for a character, product, style, or other reusable visual concept.
Open FLUX.1 TrainerTrain a FLUX.2 LoRA
Create a FLUX.2 LoRA for a character, product, brand style, or visual look in RunComfy Trainer.
Open FLUX.2 TrainerTrain a FLUX.2 Klein 4B LoRA
Train a LoRA against FLUX.2 Klein 4B for use in a compatible 4B inference setup.
Open Klein 4B TrainerTrain a FLUX.2 Klein 9B LoRA
Train a LoRA against FLUX.2 Klein 9B for use in a compatible 9B inference setup.
Open Klein 9B TrainerUse FLUX models directly
Open the FLUX Models page when you want direct model generation instead of starting from a workflow.
Browse FLUX Models