Is it normal than Chroma is slower than FLUX?

I just started using Chroma. And on my setup is roughly 2 times slower than FLUX (4s/it for FLUX vs 8s/it for Chroma). Is this normal, or i fucked up some configurations? I am using a fp8 version for both.

https://redd.it/1oxw25o
@rStableDiffusion

Yet another realistic female LoRA for Qwen

https://redd.it/1oy3xb5
@rStableDiffusion

Could I use a AI 3D scanner to make this 3D printable? I made this using SD
https://redd.it/1oy42nz
@rStableDiffusion

Some new WAN 2.2 Lightning LoRA comparisons

A comparison of all Lightning LoRA pairs, from oldest to newest.

\-All models are set to 1 strenght
\-Using FP8_SCALED base models

T2V 432x768px - EULER / SIMPLE - shift 5 - 41frames
T2I 1080x1920px - GRADIENT ESTIMATION / BONG TANGENT - shift 5 - 1frame

If you're asking me, I would tell you to use the 250928 pair, much better colors, less "high cfg" oversaturated / bright look, more natural, more overall / fine details.
Maybe try SEKO v2 if you are rendering more synthetic stuff like anime or CGI style.

Here : https://huggingface.co/lightx2v/Wan2.2-Lightning/discussions/64

https://preview.redd.it/6g0d6jpz2i1g1.jpg?width=4352&format=pjpg&auto=webp&s=cc9489b8eee7677eced827d5e9213dabcdbaf49b

https://preview.redd.it/5g1ihe7h3i1g1.jpg?width=4352&format=pjpg&auto=webp&s=5e754bd31f16fe6a13d684a5e8e6685f67e85843

https://redd.it/1oy5hjv
@rStableDiffusion