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

Use [FLUX] PuLID + LORA simple workflow (Basic, Beginner) to generate Flux images with consistent faces from a text prompt and an input image; it can apply LoRA styles or character features and provide image previews and saved images.

The workflow loads models, encodes prompts, applies PuLID, samples, decodes images, compares images, previews results, and saves images.

Provide a text prompt through CLIPTextEncode and an input image through LoadImage.

PreviewImage and SaveImage are included for image previews and saved images, while Image Comparer (rgthree) is included to compare images.

Step-by-step guidance covers connecting and configuring PuLID nodes and includes download and installation locations for required models.

Listed model files 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, LoadImage, and Power Lora Loader (rgthree).

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

The basic setup uses a GGUF model, while Options includes ClipLoader and Diffusion Model for switching to standard Flux models.

LoRA models can add specific styles or character features to generated images.

The listed base model is Flux.1 D.

Before using it, verify that your setup has the listed model files and named nodes.

Suggestion

No license is specified for this workflow, so check the applicable terms before reusing it.

Suggestion