AWPainting l Retro Illustration - SD1.5

<<<V1.0 Version>>>

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

Recommended large models: AWPinting_v1.4 or other large models from the second dimension (feel free to try different large models and return images!)

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

Recommended LoRa weights:0.6-0.8 (recommended 0.7)

Trigger words: Not required

Recommended prompt words:

The content you desire in the image (natural language, tag format is also acceptable) + additional elements

For example: Natural language: 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.

Tag:1girl,front view,full body:1.4,close up,close eyes,dark clothes,hanfu,goldn background,cloud,fog,goldn flowers(((black and white melt))).,((gold and silver lace)),(((flowing ((black)) and white background))),Floating with golden light,cinematic lighting,vanishing point

Welcome to add elements yourself or use precious prompt words~

1. Its feature is that it can generate retro style images;

2. For specific LoRA effects, please refer to the example images and the returned image area examples!

Negative prompt words recommendation:

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 best results come from the negative prompt words mentioned above! The example images are all created using these negative prompt words.

Sampling method: DPM++ 2M Karras/DPM2 a Karras (this might result in better hands)

Iterations: 30 (depending on your mood)

Recommended size: 3:4 (feel free to try other sizes as well)

Prompt word guidance coefficient (CFG): 7.0

HD resolution restoration: 4x-UltraSharp If there are images that meet the requirements, use high-definition enlargement and redraw amplitude0.3-0.4, or directly redraw with an amplitude above 0.5 for luck~

<Attention>

There is a chance that there will be issues with hands, body, and limbs in the generated images, multiple redraws might be necessary!

- Recommended direct high-definition enlargement × 2 + 0.5 redraw for luck~

- When the character is full body or small in proportion, facial collapse and blurring may occur, please enable ADetailer and selectface_yolov8n for restoration!

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

Model Usage Disclaimer:

1. You may not host this model and its derivative versions (such as fused model versions) on websites/applications intended to generate income or donations. If you intend 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 through the platform (for members, the rights of Lib platform members apply);

2. You may not directly sell images generated by this model unless you have made sufficient manual modifications to the image so that it can be fully determined as your personal work in a legal sense. If you violate this, all legal consequences will be your responsibility, and I shall not be held liable (for members, the rights of Lib platform members apply);

3. You must not intentionally use this model to create or share illegal or harmful content for dissemination and output; please abide by ethical norms and use this model for positive and constructive purposes.