this workflow works with low-Vram GPU's such as the RTX 2060

Place the GGUF model file (e.g., flux1-krea-dev-Q4_0.gguf) into the ComfyUI/models/unet directory:https://huggingface.co/QuantStack/FLUX.1-Krea-dev-GGUF/blob/main/flux1-krea-dev-Q4_0.gguf

Place the T5 XXL encoder GGUF file into the ComfyUI/models/clip directory:https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/blob/main/t5-v1_1-xxl-encoder-Q4_K_M.gguf

(workflow generation example)