Flux2 Klein Single/Dual Image Edit 9B Distilled with Lora Support — v2.0

This ComfyUI workflow is for single- or dual-image editing with LoRA support: it uses one or two source images and produces an edited image.

For a single-image edit, provide one source image; for a dual-image edit, provide two, with an edited image as the output.

Suggestion · non vérifié

Store flux-2-klein-9b-fp8.safetensors in ComfyUI/models/diffusion_models, qwen_3_8b_fp8mixed.safetensors in ComfyUI/models/text_encoders, and flux2-vae.safetensors in ComfyUI/models/vae.

Suggestion

Before downloading the models, visit BFL's repository and accept its agreement.

Suggestion

The workflow lists these model files: flux-2-klein-9b-fp8.safetensors, qwen_3_8b_fp8mixed.safetensors, and flux2-vae.safetensors.

The workflow lists the rgthree-comfy node pack at version 1.0.2512112053.

In v2.0, Power Lora Loader (rgthree) replaces LoraLoaderModelOnly for LoRA support.

The listed base model is Flux.2 Klein 9B, and the workflow version is v2.0.

Before use, verify that flux2-vae.safetensors comes from the listed Comfy-Org/flux2-dev location.

Suggestion · non vérifié