All examples were generated in just 8-10 steps (some of them are upscaled in 4-6 steps)

The fastest generation: use CFG 1.0 and set lora CFG_slider on negative -0.4 value. Lora listed in suggested resources. (CFG 1.0 ignores negative prompt. Don't use it if you need negative)

The best coherency: use CFG 2.8 and CFG_slider lora on +0.75 weight.

v4.3 [final]

It looks like a good one for me. I recommend to choose this one or v2.

Recommended settings:

• CFG 1.8 | Euler A | 8 steps

OR

• CFG 2.0 | LCM | 8 steps - better for anime and other abstract things.

Use style tags such as "anime style, flat coloring" or artist/title name. It will help model to know what you want from it.

v3.2B

Recommended settings:

• CFG 1.8

• LCM / [kl optimal / sgm uniform]

• 5-10 steps

v3.2A

Recommended settings:

• CFG 1.8 (works not bad on cfg 1 as well)

• Euler A / normal

• 5-10 steps

v1.99 (v-prediction)

Use title or artist name to get a specific style.

Eauler A - Beta scheduler (or normal)

8-16 steps

CFG: 1.0 recommended for 2x speed. Use more if you want to use negative prompt.

v2

Sampler: Euler A / Euler A cfg++

CFG: (depends on sampler)

Alternative sampler: LCM