CN Workflow-61 Children's Day Cartoon Scene ACG6-Lightflow

CN Workflow - 61 Children's Day Cartoon Scene ACG6 lightflow Hyper

File Name: 61 Children's Day Cartoon Scene ACG6-lightflow.flow

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

【This workflow is suitable for AiARTiST exclusive ACG Playground SDXL V6 version】

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

LoRA model: https://www.liblib.art/modelinfo/21d33141a1994387b575a0a91c4f20ec

(Other SDXL base models or non-LoRA can also run, CN control remains effective, but the art style may not be consistent with the example image)

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 also directly drag the control image from the example into CN)

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

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

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

Instructions: Download the Flow file to your local machine, drag it into the LightFlow plugin box, and 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

Thanks MistoLine Development Team Control Every Line!

Reference

@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 usage, achieve AI inclusiveness

Goal: Promote the inclusiveness of SD technology, make it easier to transmit AI drawing capabilities through plugins, reduce learning costs, and improve efficiency

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

Pre-processed image (can be dragged directly into the ControlNet input box), select MistoLine to apply.

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

My typical settings:

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

Default: 768 x 1536, upscale by 1.5x, HD redraw extent 0.5, redraw method Latent

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

Recommended configuration without HYPER acceleration:

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

Default: 640 x 1280, upscale by 1.5x, HD redraw extent 0.5, redraw method Latent

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

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

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

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

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

Lib members can enjoy online accelerated generation, convenient for online pairing with CADS series LoRA

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

Commercial model:

AiARTiST-CADS2.0 XL Commercial Advertising Assistance 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 to generate income or donations.

2. You may not directly sell this model and its derivative versions (such as fusion model versions) unless you have sufficiently manually modified the model to the extent that it can be fully deemed as your personal work in a legal sense. If you violate this, all legal consequences are your own responsibility, and I bear no responsibility.

3. You cannot intentionally use the model to produce or share illegal or harmful content for dissemination and output; please abide by public morals and ethics, and use this model for positive and constructive purposes.

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

For testing issues, please leave a message, business cooperation check personal homepage +V Zyuan980

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

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