Originally posted by silveroxides in his HF repo.

https://huggingface.co/silveroxides/Chroma-LoRA-Experiments/tree/main/hyper-low-step

For those who don't like the speed or stability of Chroma - use these two LoRAs (dead links, use both models from this post):

https://huggingface.co/silveroxides/Chroma-LoRA-Experiments/blob/main/hyper-low-step/Hyper-Chroma-low-step-LoRA.safetensors

https://huggingface.co/silveroxides/Chroma-LoRA-Experiments/blob/main/chroma-unlocked-rescaled_cfg_LoRA-rank_16-fp32.safetensors

Together they allow generating at cfg 1 with lower than 10 steps (8 seems to work well), which gives a very nice speed boost. If you want negative prompt to have an effect, use NAG:

https://github.com/ChenDarYen/ComfyUI-NAG

or NAGuidance node

https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NAGuidance/en.md

but keep in mind that it will decrease generation speeds.

optimal values for Normalized Attention Guidance node:

nag_scale=3.0

nag_alpha=0.25

nag_tau=1.0

nag_sigma_end=0.75