CADS Workflow - Popular Dad Shoes Design Reference - lightflow

CADS Workflow - Reference Design of Popular Dad Shoes, WebUI lightflow Hyper

File Name: CADS Workflow - Reference Design of Popular Dad Shoes - lightflow.flow

----------------------------------------------------------------------

【This workflow is suitable for CADS 2.0XL commercial design and advertising auxiliary system HYPER acceleration version】

Direct link:   https://www.liblib.art/modelinfo/a56ebacdba7d4e30b97bb124bc3fc28f

LoRA model 【CADS e-commerce series LoRA exclusive web disk】

Link: https://afdian.net/item/b232df28164311efa54e52540025c377

CN controller model: https://www.liblib.art/modelinfo/d1d7104c109948aead3d7c7b29e13aaf

CN controller model storage path: webui\models\ControlNet\

CN preprocessor method: softedge_teed (not required, you can directly drag the control chart from the download package to CN)

AiARTiST model list: https://www.liblib.art/search?keyword=AiARTiST

Free model ratio 55%, open-source model ratio 95%

Member model ratio 40%, closed-source model ratio 5%

----------------------------------------------------------------------

----------------------------------------------------------------------

Usage: Download the file package to your local system, drag it into the LightFlow plugin frame, and automatic parameter and control chart filling

LightFlow plugins are built into common web UI integration versions, if not available, they can be downloaded and installed manually (FORGE needs to be installed separately):

https://fvkij7wuqx9.feishu.cn/docx/HgZndihraotmmzxFni7cFZISnvb

Thanks MistoLine development team Control Every Line!

Quote

@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}
}

Thanks lightflow.ai development team

The Vision of LightFlow

Vision: Lower the threshold for SD use, achieve AI inclusiveness

Goal: Promote the popularization of SD technology, through plugins, making it easier to convey AI drawing capabilities, reducing learning costs, and improving efficiency

----------------------------------------------------------------------

Please download the pre-processed image and project files in a compressed package.

Flow parameters are adapted for the Hyper base model, manually change if switching to other base models.

My common configurations:

Clip Skip 1 / CFG 1 / Steps 10 / Sampler Method (Sampler) Euler a / VAE Automatic

Default: 768 x 1536, upscale 1.5x, redraw in HD amplitude 0.5, redraw method Latent

Since the final composition size is sufficient, there is no need to enable ADetailer for repairs.

Recommended configurations without HYPER acceleration:

Clip Skip 2 / CFG 7 / Steps 30 / Sampler Method DPM++ 2M Karras / VAE Automatic

Default: 640 x 1280, upscale 1.5x, redraw in HD amplitude 0.5, redraw method Latent

----------------------------------------------------------------------

Hyper-SD is one of the latest diffusion model acceleration technologies, lossless high-definition acceleration, CN adaptation is good

After testing with multiple base models, Hyper-SD can derive more image information than before acceleration!

It is highly recommended that users with 8GB of VRAM and MAC use the Hyper version, achieving 2048 HD images in just over 10 seconds

----------------------------------------------------------------------

Lib members can enjoy online accelerated generation, facilitating online matching with CADS series LoRA usage.

Model list: https://www.liblib.art/search?keyword=AiARTiST

Commercial model:

AiARTiST-CADS 2.0 XL commercial advertising auxiliary system (enterprise customization)

https://www.liblib.art/modelinfo/a56ebacdba7d4e30b97bb124bc3fc28f <<Click for direct access

----------------------------------------------------------------------

Model usage statement:

1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites/apps intended for generating revenue or donations.

2. You are not allowed to directly sell this model and its derivative versions (such as fusion model versions) unless you have made sufficient manual modifications to the model to be deemed entirely your own work in a legal sense. Any legal consequences resulting from your violation of this rule are your responsibility, and I am not responsible for them.

3. You cannot intentionally use this model to create or share illegal or harmful content for dissemination and output. Please abide by proper morals and use this model for positive and constructive purposes.

----------------------------------------------------------------------

Leave a message for testing questions, business cooperation on personal homepage +V Zyuan980

AiARTiST | Metaverse China·Shandong Digital Human/AiGC/Metaverse direction

Being a tool for artists. Serving artists. Contact details:https://afdian.net/a/AiARTiST-lib