[FLUX] PuLID simple workflow (Beginner, Basic) — v1.0

This workflow uses PuLID with Flux to generate consistent faces, with LoadImage for an image input and PreviewImage or SaveImage for image results.

PuLID node connections and settings are laid out step by step for beginners.

The image nodes are named LoadImage, PreviewImage, and SaveImage.

The workflow includes download locations and installation instructions for the required models.

Model files named for the workflow include clip_l.safetensors, FLUX_VAE_diffusion_pytorch_model.safetensors, flux1-dev-fp8.safetensors, flux1-dev-Q8_0.gguf, pulid_flux_v0.9.0.safetensors, t5xxl_fp16.safetensors, and t5xxl_fp8_e4m3fn.safetensors.

Named nodes include ApplyPulidFlux, BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoader, DualCLIPLoaderGGUF, EmptySD3LatentImage, FluxGuidance, Image Comparer (rgthree), KSamplerSelect, and LoadImage.

Other named nodes include PreviewImage, PulidFluxEvaClipLoader, PulidFluxInsightFaceLoader, PulidFluxModelLoader, RandomNoise, SamplerCustomAdvanced, SaveImage, UNETLoader, UnetLoaderGGUF, VAEDecode, and VAELoader.

The default nodes use GGUF models; the Options include ClipLoader and Diffusion Model for switching to standard Flux models.

The listed base model is Flux.1 D, and the version is v1.0.

The source page does not list a license for this workflow.