ThickPainting l - SDXL

<<<V1.0 Version>>>

Welcome back! The sample images are all produced using the SD1.5 large model <AWPainting_v1.4> + local output 4090 (N), and the local generation effect differs from the online generation!

Recommended large models: AWPinting_v1.4 or other second-dimensional large models (feel free to try different large models and return pictures!)

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

Recommended LoRa weights:0.6-0.8 (recommended 0.8)

Trigger words: Not needed

Recommended prompt words:

The content of the image you desire (recommend using natural language) + other supplementary element tags

For example: A female character wearing exquisite armor and a crown. Her armor is adorned with complex patterns and designs, primarily in silver, embellished with green gems. She has black hair and her eyes are a unique orange-yellow. Xilin holds a white lotus, standing in a sunlit forest surrounded by lush trees and green vegetation. Sunlight filters through the leaves, adding a mysterious and tranquil atmosphere to the scene.

(A female character wearing exquisite armor and a crown. Her armor is adorned with complex patterns and designs, primarily in silver, embellished with green gems. She has black hair and her eyes are a unique orange-yellow. Xilin holds a white lotus, standing in a sunlit forest surrounded by lush trees and green vegetation. Sunlight filters through the leaves, adding a mysterious and tranquil atmosphere to the scene.)

Feel free to add elements yourself or use cherished prompt words~

1. Its specialty is in generating images similar to the NIJI style;

2. For specific LoRA effects, refer to the sample images in the feedback area!

Recommended negative prompts:

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

The above negative prompts yield the best results! The sample images are all generated using these negative prompts.

Sampling method: DPM++ 2M Karras/DPM2 a Karras (perhaps this yields better hand results)

Iteration steps: 30 (depending on your preference)

Recommended size: 3:4 (feel free to experiment with other sizes)

Prompt word guidance coefficient (CFG): 7.0

HD resolution restoration: 4x-UltraSharp If there are images that meet the requirements, use high-definition enlargement, with a redraw magnitude of 0.3-0.4, or directly redraw with a magnitude of 0.5 or higher for card drawing.

<Note>

There is a chance of hands and body, limb issues in the generated image, multiple card drawings may be needed!

- Recommended direct HD enlargement × 2 + 0.5 redraw card drawing~

- If the character is full-bodied or small, facial collapse and blurred conditions may occur, please enable ADetailer and select face_yolov8n for repair!

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

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 for earning income or donations. If you intend to use this model and its derivative versions for commercial purposes (such as generative services, selling images, or publishing images on short video platforms or publications), please contact me through the platform (purchasers are subject to Lib platform membership rights);

2. You may not directly sell images generated by this model unless you have sufficiently modified the image to the extent that it can be fully classified as your personal work in legal terms. If you violate this, all legal consequences are solely your responsibility, and I am not liable (purchasers are subject to Lib platform membership rights);

3. You may not intentionally use this model to produce or share illegal or harmful content for dissemination. Please abide by public morals and use this model for positive and beneficial purposes.