ComfyUI workflow for FLUX models. The overall idea of this workflow is to be able to have more control over noise manipulations. This wflow designed to get advantage of using 2 advanced KSamplers and High-res Fix,...
Laufzeitprofil
Quellenbeschreibung
ComfyUI workflow for FLUX models. The overall idea of this workflow is to be able to have more control over noise manipulations. This wflow designed to get advantage of using 2 advanced KSamplers and High-res Fix, also provides other basic functionalities such as:
Flux model loaders including GGUF variants.
Lora stacks.
CPU transfer nodes.
Basic Txt2Img with Florence2 nodes.
Img2Img with autoresizing.
Controlnets - UnionPro and Shakkerlabs.
Ultimate SD upscaler.
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Use this ComfyUI workflow to create FLUX images from a text prompt or existing image, with preview and saving, while giving more control over noise manipulation through two advanced KSamplers and High-res Fix.
The workflow covers FLUX loading, text and image processing, sampling, ControlNets, upscaling, image preview, and image saving.
It connects to FLUX, text-encoding, vision, upscaling, and depth ControlNet models.
Enter a text prompt for text-to-image or load an existing image for image-to-image; the image-to-image path includes autoresizing.
Image results can be previewed and saved, and the workflow includes Ultimate SD upscaling.
Available features include FLUX model loaders, including GGUF variants, Lora stacks, UnionPro and Shakkerlabs ControlNets, and CPU transfer nodes.
The listed base model is Flux.1 D, the workflow is published by Nxssar, and instructions and links are included in the workflow.
Models named for this workflow include flux1-dev.safetensors; t5xxl_fp16.safetensors; flux-canny-controlnet-v3.safetensors; flux-depth-controlnet-v3.safetensors; 4x_NMKD-Siax_200k.pth; thwri/CogFlorence-2.2-Large; and ViT-L-14-BEST-smooth-GmP-TE-only-HF-format.safetensors.
Named ComfyUI nodes include AIO_Preprocessor; Anything Everywhere3; CLIPTextEncodeFlux; ControlNetApplyAdvanced; ControlNetLoader; CR Aspect Ratio; CR Image Input Switch; CR Img2Img Process Switch; CR Text Input Switch; DownloadAndLoadFlorence2Model; DualCLIPLoader; easy image;
Other named ComfyUI nodes include Fast Groups Bypasser (rgthree); Fast Groups Muter (rgthree); Florence2Run; Image Comparer (rgthree); Image Inset Crop (rgthree); Image Save; ImageResizeKJ; ImageScaleToTotalPixels; INTConstant; iToolsPromptStylerExtra; KSampler; KSamplerAdvanced;
For more control over noise manipulation, use the two advanced KSamplers and High-res Fix.
Vorschlag · nicht geprüft
Choose the text-to-image or image-to-image path, with Lora stacks, ControlNets, or Ultimate SD upscaling as applicable.
Vorschlag · nicht geprüft
Before use, verify that the listed models and ComfyUI nodes are available, including flux-canny-controlnet-v3.safetensors and ViT-L-14-BEST-smooth-GmP-TE-only-HF-format.safetensors.
Vorschlag · nicht geprüft
No license is stated for this workflow; check applicable terms before use.
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 547 downloads · Type Workflows · Base model Flux.1 D
All instructions and links provided in the workflow itself.
Remaining hardware or download-size estimates are not available yet.
Anforderungen
4x_NMKD-Siax_200k.pth
Nicht aufgelöstUpscaler · Unknown
DualCLIPLoader
MöglichText encoder · Unknown
flux-canny-controlnet-v3.safetensors
Nicht aufgelöstControlNet · Unknown
ControlNet · 1.39 GB · SAFETENSORS · Unknown
Checkpoint · 22.2 GB · SAFETENSORS · fp32 · full · Unknown
LatentUpscaleBy
MöglichUpscaler · Unknown
OverrideVAEDevice
Datei ungeprüftVAE · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
Vision model · Hugging Face · thwri/CogFlorence-2.2-Large
UltimateSDUpscale
MöglichUpscaler · Unknown
UpscaleModelLoader
MöglichUpscaler · Unknown
VAEDecode
MöglichVAE · Unknown
VAEEncode
MöglichVAE · Unknown
VAELoader
MöglichVAE · Unknown
ViT-L-14-BEST-smooth-GmP-TE-only-HF-format.safetensors
Nicht aufgelöstText encoder · Unknown
Knotenpaket · Unknown
Anything Everywhere3
GefundenKnotenpaket · Unknown
CLIPTextEncodeFlux
Nicht aufgelöstKnotenpaket · Unknown
ControlNetApplyAdvanced
MöglichKnotenpaket · Unknown
ControlNetLoader
MöglichKnotenpaket · Unknown
CR Aspect Ratio
GefundenKnotenpaket · Unknown
CR Image Input Switch
GefundenKnotenpaket · Unknown
CR Img2Img Process Switch
GefundenKnotenpaket · Unknown
CR Text Input Switch
GefundenKnotenpaket · Unknown
DownloadAndLoadFlorence2Model
MöglichKnotenpaket · Unknown
easy imageSize
GefundenKnotenpaket · Unknown
Fast Groups Bypasser (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
Fast Groups Muter (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
Florence2Run
MöglichKnotenpaket · Unknown
Image Comparer (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
Image Inset Crop (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
Image Save
GefundenKnotenpaket · Unknown
ImageResizeKJ
MöglichKnotenpaket · Unknown
ImageScaleToTotalPixels
MöglichKnotenpaket · Unknown
Knotenpaket · Unknown
Knotenpaket · Unknown
KSampler
MöglichKnotenpaket · Unknown
KSamplerAdvanced
MöglichKnotenpaket · Unknown
Load image with metadata [Crystools]
Nicht aufgelöstKnotenpaket · Unknown
LoadImage
MöglichKnotenpaket · Unknown
ModelSamplingFlux
Nicht aufgelöstKnotenpaket · Unknown
OverrideCLIPDevice
GefundenKnotenpaket · Unknown
Power Lora Loader (rgthree)
Nicht aufgelöstKnotenpaket · Unknown
Preview from metadata [Crystools]
Nicht aufgelöstKnotenpaket · Unknown
PreviewBridgeLatent
GefundenKnotenpaket · Unknown
PreviewImage
MöglichKnotenpaket · Unknown
Knotenpaket · Unknown
Prompts Everywhere
GefundenKnotenpaket · Unknown
RepeatLatentBatch
MöglichKnotenpaket · Unknown
Seed Everywhere
GefundenKnotenpaket · Unknown
ShowText|pysssss
GefundenKnotenpaket · Unknown
UNETLoader
MöglichKnotenpaket · Unknown