AiARTiST SDXL Commercial Design and Advertising Material Workflow

CFG++IPA2 All-around ComfyUI Workflow

Updated to: 07/02/2024  Striving to make ComfyUI switchable by anyone effortlessly, ready to use out of the box

Word Image: Supports CFG++ New Sampler Euler Ancestral ++ (Requires updating ComfyUI to versions after June 30) No negative words required.

Image processing: Supports crop, scale, mask, latent image importation, setting denoising (photo editing) ratio, as an auxiliary guide condition for word image

Dual LoRA Loader: Lock style weights for commercial users, support dual-column LoRA model importation, support non-accelerated model importation Hyper and other accelerators

For Easyuse users, it is convenient to switch the entire work group,Non-Easyuse users press Ctrl after selecting the component in the box and press Ctrl+B to batch switch

All manual operations or changes to the connection points are annotated with text explanations, beginner-friendly.

Workgroup and component annotations, I try to name and annotate them according to the habits of WebUI old users, reducing unfamiliarity

Looking forward to more friends joining the LiblibAI / WebUI / ComfyUI Multi-line AIGC work mode

Word Image Workflow Node List:

Load model, green is positive prompt words, red is negative prompt words (can be left blank)

Blank latent image, set output image size (default is 768x1536) modify at will

CFG++ Sampler loader, default regular version is sufficient

Scheduler Hyper Accelerated model parameters: normal steps 10 denoising (generation) range 1

Non-accelerated model parameters: Karras scheduler steps 20-45 denoising generation 1

(Note: In the image process, the denoising range here is modified to the level of changes made to the original image, with a median value of 0.5)

(Note: Hyper accelerated model parameters have very strict requirements, please do not increase the number of steps or change the sampler)

(CFG++ sampler may have overfitting with high CFG values for non-accelerated models, please reduce the CFG value)

By default, enable the [High-Resolution Enlargement] workflow, the official image processing flow of the ComfySDXL model refinement.

IPAdapter Plus v2 Comes with Full Model

Its function is to transfer the style of a single-sample image to another image, you can treat it as a real-time LoRA with only one image, commonly known as photo editing. IPAdapter accepts an image as input, encodes it as Tokens, mixes it with standard prompt words input for image generation.

The model totals 14.13GB Cloud drive link: https://pan.baidu.com/s/1fy2ygd6EeH6pbpSMa9zAPA?pwd=aigc

Extraction code: aigc   The path is preconfigured, overlay it in the Models folder under the ComfyUI root directory

The standard version used here is [IPAdapter Plus V2] process, advanced users can switch it to [Crazy Scientist] mode. In general, the standard version should already yield good results. For professional style transfer, image imitation, or master-level replication, please contact us. We have a commercial version [CADS v* *rofessional Composite Control Process] that supports hierarchical and negative condition control and can customize workflows as needed to assist content production.

AiARTiST:

https://afdian.net/a/AiARTiST-lib?tab=shop

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

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

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

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

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

Commercial model:

AiARTiST-CADS2.0 XL Business Advertising Assistance System (Enterprise Customization)

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

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

Model usage statement:

1. You may not host this model and its derivative versions (such as fusion 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 fusion model versions), unless you have made sufficient manual modifications to the model so that it can be fully determined as your personal work in a legal sense. If you violate this clause, any legal consequences caused will be your personal responsibility, and I will not be held responsible.

3. You may not intentionally use the model to create or share illegal or harmful content for dissemination and output, please abide by public morality, and use this model for positive and proactive purposes.

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

Leave a message for test questions, For business cooperation, check the individual homepage +V Zyuan980

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

Be a good tool for artists Contact information:https://afdian.net/a/AiARTiST-lib

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