CN Workflow - E-commerce Shopping Festival Scene ACG6 lightflow Hyper

File Name: CN Workflow - E-commerce Shopping Festival Scene ACG6-lightflow_lightflow.workflow

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

【This workflow is suitable for AiARTiST Specialized ACG Playground SDXL V6 Version】

Direct Link:  https://www.liblib.art/modelinfo/4bb107737a1349f7a053bbf618e46977

LoRA Model:【XL Fresh E-commerce 3DKV Visual Design】

https://www.liblib.art/modelinfo/8f9b41c7cdcb47af95470987c2db9d15

(Other SDXL basemods or no LoRA can also run, CN controls still take effect, but the style may not match the examples)

CN Controller Model: https://www.liblib.art/modelinfo/d1d7104c109948aead3d7c7b29e13aaf

CN Controller Model Storage Path: webui\models\ControlNet\

CN Preprocessor Mode: softedge_teed (optional, you can drag the control image directly into CN from the downloaded package)

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

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

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

Usage: Download the file package to your local drive, drag it into the LightFlow plugin box, and it will automatically fill in the parameters and control image

The lightflow plugin is built into common webui integrations, if not, you can download and install it yourself (FORGE needs to be installed separately):

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

Thank you MistoLine Development Team Control Every Line!

Citation

@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}
}

Thank you lightflow.ai Development Team

LightFlow Vision

Vision: Reduce the barrier to SD usage, achieve AI accessibility

Goal: Promote the accessibility of SD technology, through plugins, to easily deliver AI drawing capabilities, reduce learning costs, and increase efficiency

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

Pre-processed image (can be directly dragged into ControlNet input box), refresh the model and select MistoLine to take effect.

Flow parameters are adapted for Hyper basemod, manual changes are required when switching to other basemods.

My Common Configuration:

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

Default: 768 x 1536, HD upscale 1.5x, Redraw Ratio 0.5, Redraw Mode: Latent

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

Recommended Configuration without HYPER Acceleration:

Clip Skip 2 / CFG 7 / Steps 30 / Sampling Method DPM++ 2M Karras / VAE Auto

Default: 640 x 1280, HD upscale 1.5x, Redraw Ratio 0.5, Redraw Mode: Latent

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

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

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

It is strongly recommended for users with 8GB VRAM and MAC to use the Hyper version, producing 2048 HD images in about 10 seconds.

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

Lib members can enjoy accelerated online generation, convenient for online collaboration with the CADS series LoRA.

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

Commercial Models:

AiARTiST-CADS2.0 XL Commercial Advertisement Assistance System (Enterprise Custom)

https://www.liblib.art/modelinfo/a56ebacdba7d4e30b97bb124bc3fc28f <<Click to Direct

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

Model Usage Statement:

1. You may not host this model and its derivative versions (such as fusion model versions) on websites/apps intended to earn income or donations.

2. You may not directly sell this model and its derivative versions (such as fusion model versions) unless you have sufficiently modified the model to be fully considered your original work in a legal sense. If you violate this clause, all legal consequences are your personal responsibility, and I shall not be held responsible.

3. You may not use this model to intentionally create or share illegal or harmful content dissemination and output. Please adhere to principles of public morality and ethics, and use this model for positive and constructive purposes.

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

For testing queries, please leave a comment, for business cooperation, visit personal homepage +V Zyuan980

AiARTiST | Metaverse China · Shandong Digital Human/AiGC/Metaspace Direction

Being a tool for artists, serving artists, contact information:https://afdian.net/a/AiARTiST-lib