Sign In

ZS_buildingV1.0,单体建筑

58
770
19
Verified:
SafeTensor
Type
LoRA
Stats
770
0
Reviews
Published
Aug 22, 2023
Base Model
SDXL 1.0
Training
Steps: 5
Epochs: 50
Usage Tips
Clip Skip: 2
Trigger Words
shifanqu
Hash
AutoV2
4E8AECCC96
default creator card background decoration
Johnny_AI's Avatar
Johnny_AI

8K+ HD Building Demonstration Area

This is a model about Demonstration Area, and the base model uses SDXL1.0, which is one of the series in my architectural model, please vote 5 stars and post an image to help me, it's really important, I thank you all very much

📝 Base quality Prompt :

(masterpiece,best quality, ultra realistic,32k,RAW photo,8k uhd, high quality, film grain:1.5),

💡 Other Prompt:

  • Trigger:shifanqu,Demonstration Area

shifanqu, demonstration area, no humans,outdoors,building,,scenery, tree, sky, reflection, grass, window, 

📝 Negative Prompt :

lowres, bad anatomy, text, error, extra digit, fewer digits,cropped, worst quality, low quality, normal quality, jpeg artifacts, signature,watermark, username, blurry

📝Weight :

  • LoRA Weight : 0.5-0.7 (adjust based on the size ratio)

📝About Parameter Settings:

  • Steps : >40 (too low iterations may cause distortion)

  • Sampler : Euler a, DPM ++ SDE Karass, SDE

  • Magnify : 4x-UltraSharpm,R-ESRGAN 4X+

  • Upscale Factor : 1.5-2.0x

  • Denoising strength: 0.1-0.3

  • Recommended Size : 1536x1024, 1024x1536. Different sizes require different weights (for high-resolution restoration, a graphics card with at least 24GB is recommended)

  • CFG : 6.5-8.5 (default of 7 is recommended)

Business Collaboration:

👨🏻‍💻 Google Email: [email protected]

📢 Facebook : www.facebook.com/profile.php?id=100050585050535&mibextid=LQQJ4d

📢 Instagram : shuai0103