WLOP_SDXL_lora

This is a lora weight checkpoint that was fine-tuned using 250 higher-quality works in the WLOP portfolio. I was amazed by this style when I saw it in junior high school, so I asked the model to record it.

How to use:

tigger word: WLOP style

sampler config: euler_ancestral, normal, cfg: 4.0-5.0, timestep: 30~40 (for 768*1344), 40-55 (for 1344*768).

Note that all captions in the training set are organized in the form of adjective_noun, so when using this model, the prompt is best organized in the above form, for example:

WLOP style, zero_two_(darling_in_the_franxx), 1girl, solo, long_pink_hair, flowing_hair, soft_waves, delicate_horns, expressive_blue_eyes, large_pupils, melancholic_expression, determined_gaze, fair_skin, futuristic_bodysuit, red_bodysuit, white_accents, metallic_texture, form_fitting, quiet_strength, introspective_pose, slight_head_tilt, mechanical_background, imposing_structure, sleek_design, sharp_edges, dark_palette, blurred_background, depth_of_field, human_vs_technology_theme, emotional_intensity, close_up_shot, wide_angle_lens, low_angle_view, commanding_presence, dramatic_lighting, warm_vs_cold_contrast, oni_horns, white_hairband, pilot_suit, makeup, eyeshadow, floating_hair, mecha, robot, looking_at_viewer, open_mouth, bangs, upper_body

You can use detailed_facial_features,beautiful eyes, beautiful face, delicate face, focus on face, to enhance the facial quality.

Training resolution: 1344*768 (Background and perspective in the style of Ghost Blade works), 768*1344 (Recommended for portraits)

support 1024*1024