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,...
Runtime profile
Source description
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.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this ComfyUI workflow for FLUX text-to-image and image-to-image creation: enter a text prompt or existing image, use two advanced KSamplers and High-res Fix for more control over noise manipulation, and produce images for preview or saving with ControlNets and upscaling.
The workflow has listed model connections for FLUX, text encoding, vision, upscaling, and depth ControlNet components.
Named components cover FLUX loading, text and image processing, sampling, ControlNets, upscaling, image preview, and image saving.
Enter a text prompt for text-to-image or an existing image for image-to-image; the image-to-image path includes autoresizing.
Use FLUX model loaders, including GGUF variants, Lora stacks, CPU transfer nodes, ControlNets from UnionPro and Shakkerlabs, and Ultimate SD upscaling.
The listed base model is Flux.1 D, the publisher is Nxssar, and instructions and links are included in the workflow.
Named model files are 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 workflow’s two advanced KSamplers and High-res Fix.
Suggestion · not verified
Choose the text-to-image or image-to-image path, then add Lora stacks, ControlNets, or Ultimate SD upscaling for the task.
Suggestion · not verified
Before using it, verify that the listed model files and ComfyUI nodes are available.
Suggestion · not verified
No license is stated for this workflow; check applicable terms before use.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 547 downloads · Type Workflows · Base model Flux.1 D
All instructions and links provided in the workflow itself.
Estimated VRAM requirement
Estimate unavailable
32.7 GB across 4 of 15 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
52 requirementsUpscaler · 63.9 MB · PT · Unknown
DualCLIPLoader
Not resolvedText encoder · Unknown
flux-canny-controlnet-v3.safetensors
Not resolvedControlNet · Unknown
ControlNet · 1.39 GB · SAFETENSORS · Unknown
Checkpoint · 22.2 GB · SAFETENSORS · fp32 · full · Unknown
LatentUpscaleBy
Not resolvedUpscaler · Unknown
OverrideVAEDevice
Not resolvedVAE · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
Vision model · Hugging Face · thwri/CogFlorence-2.2-Large · CogFlorence 2.2 Large
UltimateSDUpscale
Not resolvedUpscaler · Unknown
UpscaleModelLoader
Not resolvedUpscaler · Unknown
VAEDecode
Not resolvedVAE · Unknown
VAEEncode
Not resolvedVAE · Unknown
VAELoader
Not resolvedVAE · Unknown
ViT-L-14-BEST-smooth-GmP-TE-only-HF-format.safetensors
Not resolvedText encoder · Unknown
AIO_Preprocessor
Not resolvedNode pack · Unknown
Anything Everywhere3
Not resolvedNode pack · Unknown
CLIPTextEncodeFlux
Not resolvedNode pack · Unknown
Node pack · Unknown
ControlNetLoader
Not resolvedNode pack · Unknown
CR Aspect Ratio
Not resolvedNode pack · Unknown
CR Image Input Switch
Not resolvedNode pack · Unknown
CR Img2Img Process Switch
Not resolvedNode pack · Unknown
CR Text Input Switch
Not resolvedNode pack · Unknown
DownloadAndLoadFlorence2Model
Not resolvedNode pack · Unknown
easy imageSize
Not resolvedNode pack · Unknown
Fast Groups Bypasser (rgthree)
Not resolvedNode pack · Unknown
Fast Groups Muter (rgthree)
Not resolvedNode pack · Unknown
Florence2Run
Not resolvedNode pack · Unknown
Image Comparer (rgthree)
Not resolvedNode pack · Unknown
Image Inset Crop (rgthree)
Not resolvedNode pack · Unknown
Image Save
Not resolvedNode pack · Unknown
ImageResizeKJ
Not resolvedNode pack · Unknown
ImageScaleToTotalPixels
Not resolvedNode pack · Unknown
INTConstant
Not resolvedNode pack · Unknown
iToolsPromptStylerExtra
Not resolvedNode pack · Unknown
KSampler
Not resolvedNode pack · Unknown
KSamplerAdvanced
Not resolvedNode pack · Unknown
Load image with metadata [Crystools]
Not resolvedNode pack · Unknown
LoadImage
Not resolvedNode pack · Unknown
ModelSamplingFlux
Not resolvedNode pack · Unknown
OverrideCLIPDevice
Not resolvedNode pack · Unknown
Power Lora Loader (rgthree)
Not resolvedNode pack · Unknown
Preview from metadata [Crystools]
Not resolvedNode pack · Unknown
PreviewBridgeLatent
Not resolvedNode pack · Unknown
PreviewImage
Not resolvedNode pack · Unknown
PromptBuilder //Inspire
Not resolvedNode pack · Unknown
Prompts Everywhere
Not resolvedNode pack · Unknown
RepeatLatentBatch
Not resolvedNode pack · Unknown
Seed Everywhere
Not resolvedNode pack · Unknown
ShowText|pysssss
Not resolvedNode pack · Unknown
UNETLoader
Not resolvedNode pack · Unknown