Description
--------------------------------------------------------------------------------
AiARTiST-CADS2.0-Hyper-RAY XL Interior Design Rendering System
Filename: AiARTiST_HyperRAY_interior_design_selected.safetensors
Built-in Accelerator Accelerator: Hyper-SDXL | Faster than Lightning Design Rendering
Hyper-SD is one of the latest diffusion model acceleration technologies, lossless high-definition acceleration, well-adapted for CN
Through multiple base model tests, Hyper-SD can derive more image information than before acceleration!
It is highly recommended for interior design users to use the Hyper version,CADS-HyperRAY XL join the group to obtain
Be a tool for artists Contact:https://afdian.net/a/AiARTiST-lib +v zyuan980
----------------------------------------------------------------------
Parameters Configuration for CADS-HyperRAY XL:(Very Important)
Clip Skip 1 / CFG 1 / Steps 10 / Sampler: Euler a / VAE Auto
Size: 1280x720 / 1536x768 / 960x1920 / 1920x960 / 2048x1024 / 1024x2048
For output sizes larger than 1536, it is recommended to enable Kohya HRFix plugin to correct composition errors and enhance corrections
Avoid negative words, no need to fill in negative words, well-adapted for LoRA and ControlNet.
----------------------------------------------------------------------
ControlNetXL (CNXL)- A collection of Controlnet models for SDXL
ControlNet models list for SDXL: (Thanks to the big guys, please reward before downloading)
Highly Recommended MistoLine — Control Every Line!
MistoLine is a model that can adapt to any type of line draft, with high accuracy and excellent stability for SDXL-ControlnetNet models. It can generate high-quality images (short side greater than 1024px) based on any type of line draft input by the user (hand-drawn, various controlnet-line preprocessors, model line wireframes, etc.), without the need to select different controlnet models based on different line preprocessors. MistoLine has good generalization ability under various line draft conditions.
Trained by TheMisto.ai (Shenzhen Mixed Tuple Technology Co., Ltd.), this model is compatible with most SDXL models except (PlaygroundV2.5 and CosXL), and can be used in conjunction with LCM and other ControlNet models. We open-source the corresponding model weight files for personal users for non-commercial use.
Download the mistoLine_rank256 version in the platform: https://www.liblib.art/modelinfo/d1d7104c109948aead3d7c7b29e13aaf
Download address in China (Mainland):
Link: https://pan.baidu.com/s/1DbZWmGJ40Uzr3Iz9RNBG_w?pwd=8mzs
Citations
@misc{
title={Adding Conditional Control to Text-to-Image Diffusion Models},
author={Lvmin Zhang, Anyi Rao, Maneesh Agrawala},
year={2023},
eprint={2302.05543},
archivePrefix={arXiv},
primaryClass={cs.CV}
}ControlNet XL Models List:
bdsqlsz: canny | depth | lineart-anime | mlsd-v2 | normal | FAQ













