This is a realistic/photographic/artistic style LoRA trained on Qwen-image, performing decently across various style types.

You can refer to the sample images for generation guidance, or check out the images shared in the community showcase area.

Currently, generation is mainly done via WebUI, so you can also use WebUI.

Prompt reference:

Outdoor photography, beautiful woman portrait, summer white outfit, long ponytail, natural, gentle breeze, beautiful messy hair, dynamic turn around, roadside, relaxed vibe, close-up, eye-level shot, eye close-up, wide-angle lens, overexposed, sense of depth, soft side light, light and shadow contrast, soft focus, film grain, fresh Japanese style, cool tones, lens aesthetics, cinematic texture, high-end feel, masterpiece,

Use cases: Portrait photography, atmospheric posters, artistic photography

Recommended model parameters:

Sampling method: Euler

Recommended aspect ratio: Both 3:4 and 9:16 work well

Sampling steps: 26~37

CFG scale: 4

Model weight: 0.85