ComfyUI CAD2XL Product Replacement Workflow LayerStyle Hyper

File Name: CADS2XLHyper_Layerstyle_05162302.json

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

【This workflow is suitable for CADS2.0XL Hyper commercial design and advertising support system】

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

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

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

Usage Method: Download to local, drag into ComfyUI, install missing nodes

【Detailed configuration instructions and usage instructions are being perfected and will be added later】

Main module: ComfyUI_LayerStyle author's release page usage:

https://github.com/chflame163/ComfyUI_LayerStyle/blob/main/README_CN.MD#SegmentAnythingUltra

Main Nodes: SegmentAnythingUltraV2

Upgrade version of SegmentAnythingUltra, added VITMatte edge processing method.

*Please refer to the installation method of ComfyUI Segment Anything to install the model. If you have correctly installed ComfyUI Segment Anything, you can skip this step.

• Download config.json, model.safetensors, tokenizer_config.json, tokenizer.json, and vocab.txt 5 files from here to the ComfyUI/models/bert-base-uncased folder.
• Download GroundingDINO_SwinT_OGC config file, GroundingDINO_SwinT_OGC model, GroundingDINO_SwinB config file, GroundingDINO_SwinB model to the ComfyUI/models/grounding-dino folder.
• Download sam_vit_h, sam_vit_l, sam_vit_b, sam_hq_vit_h, sam_hq_vit_l, sam_hq_vit_b, mobile_sam these files to the ComfyUI/models/sams folder.

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

Model Recommendations:

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

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

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

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

It is highly recommended for advertising design users to use the Hyper version, CADS2.0-Hyper XL supports enterprise customization

Be a good toolman, serve artists, contact information: https://afdian.net/a/AiARTiST-lib +v zyuan980

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

Parameters configuration for CADS-HyperRAY XL: (Very Important)

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

Size: 1280x720 / 1536x768 / 960x1920 / 1920x960 / 2048x1024 / 1024x2048

For output size larger than 1536, it is recommended to open Kohya HRFix plugin to correct composition errors and amplify corrections.

Avoid negative words, no need to fill in negative words, good adaptation for LoRA and ControlNet.

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

Model Usage Statement:

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

2. You may not directly sell this model and its derivative versions (such as fused model versions) unless you have made sufficient manual modifications to the model so that it can be fully considered as your personal work in a legal sense. If you violate this clause, you will be personally responsible for all legal consequences; I shall not be held responsible.

3. You cannot intentionally use the model to produce or share illegal or harmful content for dissemination and output. Please uphold good morals and ethics and use this model for positive and constructive purposes.

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

For testing questions, please leave a message, the local running version is open source For business cooperation, check the personal homepage +V Zyuan980

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

Be a good toolman, serve artists, contact information: https://www.liblib.art/search?keyword=AiARTiST

————————————————————————————————————————