Type: LORAModel introduction: LORA uses modern and minimalist style pictures for training. High-definition pictures are selected (2K-6K). The training pictures are derived from high-definition renderings. Very fine and reasonable structure are the selection conditions. This LORA is mainly about style control.Base film recommendations: (large realistic models)Model refining base film: Laowang_Architecutral_MIX V0.5Recommendations: In no particular orderLaowang_Architecutral_MIX V0.5majicMIX realisticMoyou Man-Made ManSampling Steps : 30-40Sampling method : EulerSize recommendation: Both horizontal and vertical are acceptable (high-resolution restoration can be enabled)Without ControlNet, 512*512 is recommendedAdding ControlNet512*768 will also have a good effectAmplification algorithm:8x-NMKD-SuperscaleBasic AlgorithmBasic Algorithm 1.5Trigger WordsOfficeTesting ControlNetOffice, modern design, color block design, geometric design, modern geometry, minimalism, cleanliness, public environment, Negative prompt: NSFW, (worst quality:2), (low quality:2), (normal quality:2), lowres, (monochrome), (grayscale), blurry, signature, drawing, sketch, text, word, logo, cropped, out of frame, skin spots, acnes, skin blemishes, age spot, (ugly:1.2), (duplicate:1.2), (morbid:1.21), (mutilated:1.2), (tranny:1.2), mutated hands, (poorly drawn hands:1.5), blurry, (bad anatomy:1.2), (bad proportions:1.3), extra limbs, (disfigured:1.2), (missing arms:1.2), (extra legs:1.2), (fused fingers:1.5), (too many fingers:1.5), (unclear eyes:1.2), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (extra arms and legs), people,NSFW,man,face,distorted person,blur,blurry,(distorted lines:2),(worst quality:2),(low quality:2),monochrome,grayscale,drawing,painting,crayon,sketch,graphite,soft,deformed,ugly,dirt,graying,wrong perspective,signature,text,word,logo,cropped,out of frame,nsfw Steps: 28, Sampler: Euler a, CFG scale: 7.0, Seed: 2351030680, Size: 512x512, Model hash: 5350dfc29c, Model: （不同大模型）, Denoising strength: 0.27, Clip skip: 2, ENSD: 31337, RNG: CPU, Lora 1: 20240219-1708311549958-0020, Lora Hash 1: 3b4542ac95, Lora Weight 1: 0.8, Controlnet 0: "preprocessor: depth_leres (LeRes 深度图估算）, model: control_v11f1p_sd15_depth, weight: 1.0, starting/ending: (0.0, 1.0), resize mode: Crop and Resize, pixel_perfect: False, control mode: Balanced, preprocessor params: (512, 0, 0)", vae_name: automatic, Hires resize: 1024x1024, Hires steps: 20, Hires upscaler: 8x-NMKD-Superscale

Modern Office SD1.5

现代化办公室SD1.5_v1.0.safetensors

v1.0

Type: LORAModel introduction: LORA uses modern and minimalist style pictures for training. High-definition pictures are selected (2K-6K). The training pictures are derived from high-definition renderings. Very fine and reasonable structure are the selection conditions. This LORA is mainly about style control.Base film recommendations: (large realistic models)Model refining base film: Laowang_Architecutral_MIX V0.5Recommendations: In no particular orderLaowang_Architecutral_MIX V0.5majicMIX realisticMoyou Man-Made ManSampling Steps : 30-40Sampling method : EulerSize recommendation: Both horizontal and vertical are acceptable (high-resolution restoration can be enabled)Without ControlNet, 512*512 is recommendedAdding ControlNet512*768 will also have a good effectAmplification algorithm:8x-NMKD-SuperscaleBasic AlgorithmBasic Algorithm 1.5Trigger WordsOfficeTesting ControlNet

Files with SHA256: 3b4542ac9564bf0843286836fbf93f9f2d9953f8091779cce65ae3f505bc646e