[LoRA] Smokemancer
模型介绍：Smoke 'em if you got 'em..
A model to help generate random smoke effect around your character. Trained on mostly realistic images. Comes in eight seven colors. Use the trigger prompts accordingly..
Weight: 0.7 - 0.9
Trigger:
▣ blue-smoke
▣ green-smoke
▣ orange-smoke
▣ purple-smoke
▣ red-smoke
▣ white-smoke
▣ yellow-smoke
▣ black-smoke ( Doens't work as well. Needs to be in a bright or white background)
Additional tags: smoke everywhere, swirling smoke (in case they don't appear as much)
Side effect: May turn the color of your clothing to the same color as the smoke. I'll try to fix it in an update in the future..
p/s: If you're leaving a review, consider sharing your generated images too. I love looking at your creations..
Buy me a coffee.. ☕
https://www.buymeacoffee.com/samirfan90
~~~~~~~~~~~~~~~~~~~~~~~o(*￣︶￣*)o~~~~~~~~~~~~~~~~~~~~~~~
示例提示词和参数：
Prompt: realistic, ((masterpiece)), ((best quality)), (detailed), cinematic, dynamic lighting, soft shadow, detailed background, professional photography, depth of field, intricate, detailed face, subsurface scattering, realistic hair, realistic eyes, muscular, manly, photo of a handsome man, purple-smoke, swirling smoke everywhere, dynamic pose, fighting stance, punk jacket, torn clothes, t-shirt, ripped jeans, gas mask, messy hair, outdoors, urban, city, street, post-apocalypse,
Negative prompt: 1girl, feminine face, low quality face, deformed face, deformed penis, 3d rendering, cgi, cartoon, lowres, worst quality, grayscale, monochrome, watermark, bad-hands-5, verybadimagenegative_v1.3, ng_deepnegative_v1_75t,
Steps: 35, CFG scale: 7, Sampler: DPM++ 2M SDE Karras, Seed: 254887715, Size: 512x768, Model: HomoFidelis_v1.5, Version: v1.5.1, Model hash: f33e1466a1, "bad-hands-5: aa7651be154c, Hires upscale: 2, AddNet Enabled: True, AddNet Model 1: Concept - Smokemancer(6f360558257d), Hires upscaler: R-ESRGAN 4x+, ADetailer model: face_yolov8n.pt, AddNet Module 1: LoRA, Face restoration: CodeFormer, ADetailer version: 23.8.0, AddNet Weight A 1: 0.7, AddNet Weight B 1: 0.7, Denoising strength: 0.35, ADetailer mask blur: 4, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ng_deepnegative_v1_75t: 54e7e4826d53", ADetailer inpaint padding: 32, verybadimagenegative_v1.3: d70463f87042, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, Clip skip: 2
页:
[1]