gguf quantized and fp8 scaled aura

setup (once)

drag aura_flow_0.3_q4_0.gguf [3.95GB] to > ./ComfyUI/models/diffusion_models
drag aura_flow_0.3_fp8_scaled.safetensors [9.66GB] to > ./ComfyUI/models/checkpoints
drag aura_vae.safetensors [167MB] to > ./ComfyUI/models/vae

run the .bat file in the main directory (assuming you are using the full pack below)
drag the workflow json file (below) to > your browser

drag any workflow json file to the activated browser; or
drag any generated picture (which contains the workflow metadata) to the activated browser
workflow for safetensors (fp8 scaled version above is recommended)
workflow for gguf (opt to use the aura vae; but for the text encoder, since the unique format of that separate clip was not supported by comfyui yet, for the time being, use the one embedded inside fp8 scaled safetensors would be a better choice, it won't affect the speed, as the model will be loaded from gguf instead)