Flux Daily Driver — v1.1
There are only a couple of small updates but I think they're useful enough to merit posting a new version.
Laufzeitprofil
- Zugriff
- Externer Arbeitsablauf
- Status
- Aufgelistet
- Version
- Flux Daily Driver v1.1.json
- Quelle
- Civitai
- Aktualisiert
- 3. Nov. 2026
Quellenbeschreibung
There are only a couple of small updates but I think they're useful enough to merit posting a new version.
Replaced a couple of nodes that are no longer supported by the latest version of ComfyUI
Replaced the TeaCache node with a new one that can be more easily installed
Updated the Seed node and random seeding for the Dynamic Prompts custom node (see below)
In version 1.0, the dynamic prompt node had its own randomized seed that was separate from the main Seed node that's visible in the workflow. This made it hard to re-try an image several times if dynamic prompts were in use since you had to go track down the other seed node and set it to Fixed. In this new version, the one seed value is plugged into everything that uses a random seed. If you restore a workflow from an image and re-run it, you will get the same "random" results from that restored seed value across the whole workflow.
I tried setting up a different image saver to store Civitai metadata with the image, but none of the nodes worked well for me. They either gave me problems with the sampler, scheduler, and/or model name, or they had other minor issues that bugged me. If anyone knows of a good custom node for this job, ideally one where all the extra metadata can be gathered in a standalone node to keep the Save Image window clean and simple, please drop a comment about it.
Anforderungen
Modelle
10- Gefunden
Upscaler · 63.9 MB · PTH · Unknown
- Datei angegeben
VAE · 878 MB · Hugging Face · aka7774/comfyui-models
clip_l.safetensors
MöglichText encoder · Unknown
- Datei angegeben
Diffusion model · 5.38 GB · Hugging Face · PincoLi/ComfyUI-model-pack
- Gefunden
Checkpoint · 123 MB · SAFETENSORS · Unknown
msFluxSFWNSFWV3_ggufQ4KS.gguf
Nicht aufgelöstDiffusion model · Unknown
sigclip_vision_patch14_384.safetensors
Nicht aufgelöstClip Vision · Unknown
t5-v1_1-xxl-encoder-Q4_K_S.gguf
GefundenText encoder · 2.55 GB · GGUF · Unknown
t5xxl_fp8_e4m3fn.safetensors
Nicht aufgelöstText encoder · Unknown
Unresolved model selection: Power Lora Loader (rgthree)
Nicht aufgelöstLoRA · Unknown
Knotenpakete
16Knotenpaket · GitHub · kaibioinfo/ComfyUI_AdvancedRefluxControl
- Gefunden
Knotenpaket · GitHub · Suzie1/ComfyUI_Comfyroll_CustomNodes
comfyui_ultimatesdupscale
GefundenOptionalKnotenpaket · Registry
comfyui-custom-scripts
GefundenKnotenpaket · Registry
- Gefunden
Knotenpaket · Registry
- Gefunden
Knotenpaket · GitHub · city96/ComfyUI-GGUF
comfyui-kjnodes
GefundenKnotenpaket · Registry
derfuu_comfyui_moddednodes
GefundenKnotenpaket · Registry
- Gefunden
Knotenpaket · GitHub · adieyal/comfyui-dynamicprompts
Fast Groups Bypasser (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
GetNode
Nicht aufgelöstKnotenpaket · Unknown
- Gefunden
Knotenpaket · GitHub · giriss/comfy-image-saver
pr-was-node-suite-comfyui-47064894
Nicht aufgelöstKnotenpaket · Registry
rgthree-comfy
GefundenKnotenpaket · Registry
SetNode
Nicht aufgelöstKnotenpaket · Unknown
teacache
MöglichOptionalKnotenpaket · Registry
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Zweck
Flux Daily Driver is a ComfyUI workflow for generating Flux images from text prompts, applying Redux image-to-image guidance to input images, and upscaling images with SD Ultimate Upscale.
Fluss
It combines basic Flux rendering, Redux image-to-image guidance, and SD Ultimate Upscale in one compact workflow.
The layout puts frequently edited controls beside a single large image preview and keeps less frequent edits just off screen.
Eingaben und Ausgaben
Enter prompts in two parts to support styles, and use wildcard-based dynamic prompts.
Use an input image for Redux image-to-image guidance, then use SD Ultimate Upscale to enlarge images.
Einrichtung
The listed base model is Flux.1 D, and the workflow supports Diffusion model files in .safetensors format and GGUF.
The listing identifies publisher darkroast175696 and does not list a license.
Abhängigkeiten
The named model files are: 4x-UltraSharp.pth, ae.safetensors, clip_l.safetensors, flux1-dev-fp8.safetensors, flux1-redux-dev.safetensors, msFluxSFWNSFWV3_ggufQ4KS.gguf, sigclip_vision_patch14_384.safetensors, t5-v1_1-xxl-encoder-Q4_K_S.gguf, and t5xxl_fp8_e4m3fn.safetensors.
The named node packs include: advancedRefluxControl, comfyroll, comfyui_ultimatesdupscale, comfyui-custom-scripts, comfyui-easy-use, and comfyui-gguf.
Other named node packs include: comfyui-kjnodes, derfuu_comfyui_moddednodes, dynamicprompt, image-saver, pr-was-node-suite-comfyui-47064894, rgthree-comfy, and teacache.
Konfiguration
Keep prompt text, guidance, and steps near the preview when those are the controls you edit most often.
Vorschlag · nicht geprüft
Vorsichtsmaßnahmen
Before use, check these model filenames in your local ComfyUI setup: 4x-UltraSharp.pth, ae.safetensors, flux1-dev-fp8.safetensors, msFluxSFWNSFWV3_ggufQ4KS.gguf, t5-v1_1-xxl-encoder-Q4_K_S.gguf, and t5xxl_fp8_e4m3fn.safetensors.
Vorschlag · nicht geprüft
Also check these node-pack names in your local ComfyUI setup: teacache, pr-was-node-suite-comfyui-47064894, comfyui-gguf, comfyroll, image-saver, dynamicprompt, and advancedRefluxControl.
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 Quelle
Quellen
1 QuelleWorkflow instructions
Author notes from Flux Daily Driver v1.1.json · selected release
# Online Resources * Flux on ComfyUI tutorial: <https://stable-diffusion-art.com/flux-comfyui/> * Install [ComfyUI Manager](https://stable-diffusion-art.com/comfyui-manager-install/) Once ComfyUI Manager is installed and you've restarted the ComfyUI server, the Manager will alert you about any custom nodes in this workflow that you might be missing in your installation. The Manager utility can find, download, and install all of those for you with just a couple of mouse clicks. # Downloads to get started These files are the ones most often used for personal use of Flux in ComfyUI. There are many other files that can be used, like alternate checkpoints in place of flux1-dev-fp8 for example, but these files will be enough to get you started with this workflow. Refer to the tutorial linked above for instructions on where to place these files in your ComfyUI directory. * <https://huggingface.co/Comfy-Org/flux1-dev/blob/main/flux1-dev-fp8.safetensors> * <https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors> * <https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/t5xxl_fp8_e4m3fn.safetensors> * <https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/ae.safetensors> * My favorite upscale models, save to `<comfyui directory>/models/ERSGAN` - <https://openmodeldb.info/models/4x-UltraSharp> - <https://openmodeldb.info/models/1x-ITF-SkinDiffDDS-v1> - <https://huggingface.co/WAS/8x_NMKD-Faces_160000_G/tree/main> * Image-to-Image with Redux from Black Forest Labs - <https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev/blob/main/flux1-redux-dev.safetensors> save to `Comfyui/models/style_models` directory - <https://huggingface.co/Comfy-Org/sigclip_vision_384/blob/main/sigclip_vision_patch14_384.safetensors> save to `Comfyui/models/clip_vision` directory
Author notes from Flux Daily Driver v1.1.json · selected release
Generated output appears here. Multiple images may appear in the box below depending on which features you have enabled.
Author notes from Flux Daily Driver v1.1.json · selected release
All of the complex parts of this workflow are shoved over to the far right. If you want to see how things plug together, or if you want to adjust something in the workflow, you can find most major sections of the system grouped and labeled.
Author notes from Flux Daily Driver v1.1.json · selected release
Image-to-Image uses Redux for image matching. Upscale settings are below. Your new image does not need to match the dimensions of the source image but some cropping of the source may occur. Crop settings are found to the far right.
Author notes from Flux Daily Driver v1.1.json · selected release
Upscale factor will determine the final dimensions of the output image. These dimensions will override any settings you make in the Image Size box. Upscale De-noise ranges from 0 to 1. 0 means no interpolation at all, so output quality may appear slightly blurry as if a primitive upscale were used. Higher values will introduce more AI-generated detail into the image. This will change the source image in order to preserve clarity and detail. Find a balance for your image: high enough to add detail but low enough that your source image isn't changed too much. There are MANY upscale models to choose from and find online. In my experience, 4x-UltraSharp gives the best general purpose performance, but different models are good at different things. Just download several and try them out.
Author notes from Flux Daily Driver v1.1.json · selected release
Uploaded images will be ignored unless you have enabled Upscale or Image-to-Image.
Author notes from Flux Daily Driver v1.1.json · selected release
I HIGHLY recommend hiding the connector lines in this workflow. ComfyUI has a tool panel in the lower-right corner. Click the Eye icon to hide/show connection lines.
Author notes from Flux Daily Driver v1.1.json · selected release
It's usually best to enable EITHER new image generation OR image upscale. You can do both at the same time, but all of the settings will apply to both AND the output dimensions of the upscaled image must match the new image or the build will fail. Just stick to one at a time; it's easier.
Author notes from Flux Daily Driver v1.1.json · selected release
Enter the text for your positive prompt. The Prompt Suffix Box is provided to allow a separate entry of common style information that you don't want to edit as often. This prompt supports wildcards using comfyui-dynamicprompts from https://github.com/adieyal/comfyui-dynamicprompts I recommend creating wildcard files for different styles to use in the Prompt Suffix box. You can use style text here as a starting point: https://stable-diffusion-art.com/sdxl-styles/ The randomized prompt being used for the image is displayed below.
Author notes from Flux Daily Driver v1.1.json · selected release
Notes and prompt snippets can be entered here.
Author notes from Flux Daily Driver v1.1.json · selected release
TeaCache can boost the speed of your renders at the expense of image output quality. The strength of the TeaCache ranges from 0 to 1, where 0 is no TeaCache change at all and 1 strongest cache with lowest quality. See https://github.com/welltop-cn/ComfyUI-TeaCache for more information.
Download files
Modellartefakte
2 Artefakte
Modellartefakte
2 ArtefakteQuellenauszüge
3 Auszüge
Quellenauszüge
3 AuszügeSource context: 701 downloads · Type Workflows · Base model Flux.1 D
Source context: 682 downloads · Type Workflows · Base model Flux.1 D
Source context: 645 downloads · Type Workflows · Base model Flux.1 D
