Z-Image-Art Scene Base Version，using a multimodal training set enhances multi-style and multi-scene capabilities, increasing diversity and strengthening style. The training set does not include human, so its impact on character face is relatively small.

Recommended settings: euler_ancesral + beta, 30 steps, 4 cfg, 0.6-1 weight

For more detail or to include people, try using Z-Image Base-Add details and Z-Image-Aesthetic. Their main function is to enhance style and improve the appearance of people; please experiment with them.

Have fun!