ClayWord l Clay World - SDXL

<<<Version 1.0>>>

Remember to return the image! All sample images are produced locally on 4090 (N), the effect is different from online generation!

Recommended large model: SDXL Basic_1.0

https://www.liblib.ai/modelinfo/1fd281cf6bcf01b95033c03b471d8fd8

Recommended LoRa weight:0.8

Trigger words:Caly style

Recommended prompt words:

Caly style (need to fill in trigger words) + desired image content (in natural language) + other additional tags

Welcome to add elements on your own or use treasure prompt words~

1. It can generate clay style images, but the specific effect is between PVC and clay; (Personally prefer a PVC-like feel on faces)

2. It is recommended to output images at around 1024 resolution and then perform 1.5x HD restoration;

3. Please refer to example images and the returned image area for specific LoRa effects!

Recommended negative prompt words:

nsfw, (low quality, normal quality, worst quality, jpeg artifacts), cropped, monochrome, lowres, low saturation, ((watermark)), (white letters), skin spots, acnes, skin blemishes, age spot, mutated hands, mutated fingers, deformed, bad anatomy, disfigured, poorly drawn face, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, out of focus, long neck, long body, extra fingers, fewer fingers, (multi nipples), bad hands, signature, username, bad feet, blurry, bad body,

or

ng_deepnegative_v1_75t, (badhandv4:1.2), (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)) watermark, moles

Sampling method: Euler a / DMP++2M Karras / Restart (whichever you prefer, depending on your mood)

Iteration steps: 30 (depending on your mood)

Recommended sizes: 1:1/2:3/3:2/3:4/4:3/9:16/16:9 (feel free to try other sizes)

GUIDE Coefficient for Prompt Words (CFG): 7.0

HD Resolution Restoration: 4x-UltraSharp If there are images that meet the requirements, use high-definition enlargement, redraw range0.3-0.4, or directly redraw range above 0.5 for Gacha~

<Attention>

There is a chance of hands and body, limbs issues in the generated images, multiple Gachas are needed! Also, due to the art style, details like hands and feet are often not distinct~

- If conditions permit, it is recommended to download and use locally~

- For full-body or smaller proportions, the face may appear distorted or blurry, please enable ADetailer and selectface_yolov8nfor restoration!

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

Model Usage Disclaimer:

1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites/applications intended to earn income or donations. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, publishing images on short video platforms, or publications, etc.), please contact me via the website;

2. You are not allowed to directly sell images generated by this model unless you have made sufficient manual modifications to the image to the extent that it can be fully identified as your own work in a legal sense. If you violate this clause, you will be personally liable for all legal consequences, I shall not be held responsible;

3. You may not use this model to deliberately create or share illegal or harmful content for dissemination and output, please abide by proper conduct and use this model for positive purposes.