Simple and Versatile ComfyUI Workflow for Flux — v1.0

This ComfyUI workflow is for generating and enhancing images with Flux. It takes text prompts or existing images and can create, transform, face-swap, and upscale images.

Its flow includes loading and scaling images, encoding and decoding latents, sampling, face swapping, and saving images.

Use a text prompt for text-to-image creation or an existing image for image-to-image changes; the result is an image that can be generated, modified, face-swapped, or upscaled.

This is version v1.0, based on Flux.1 D, and published by Alienkilla47735.

This is a workflow, and no Pipe version is provided.

Named model files include 4x-UltraSharp.pth, clip_l.safetensors, codeformer.pth, flux_dev.safetensors, FLUX-dev-lora-add_details.safetensors, inswapper_128.onnx, and t5xxl_fp8_e4m3fn.safetensors.

Named node components include BasicGuider, BasicScheduler, CLIPTextEncode, CR Img2Img Process Switch, CR LoRA Stack, CR Upscale Image, DualCLIPLoader, easy loraStackApply, EmptyLatentImage, Get Image Size (JPS), ImageScale, and KSamplerSelect.

Additional node components are LoadImage, RandomNoise, ReActorFaceSwap, SamplerCustomAdvanced, SaveImage, SDXL Resolutions (JPS), UNETLoader, VAEDecode, VAEEncode, VAELoader, and WD14Tagger|pysssss.

For prompt-based creation, choose text-to-image; for modifying an existing image, choose image-to-image.

Suggestion · non vérifié

Choose face swapping to replace a face, or upscaling to improve image resolution.

Suggestion · non vérifié

Before use, verify that the named node components are available in your ComfyUI setup.

Suggestion · non vérifié

A license is not specified for this workflow.