LineDrawing l Black and White Sketch-SD1.5

<<<Version 1.0>>>

Welcome back! Sample images are all using the SD1.5 large model <AWPainting_v1.4> + 4090 local images (N), the local generation effect is different from online generation!

Recommended large models: AWPinting_v1.4 or other anime-style large models (feel free to try different large models and return with images!)

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

Recommended LoRa weights:0.8-1 (recommended 0.8)

Trigger words: This is a line drawing of

Recommended prompt words:

This is a line drawing of + the content you want to see in the image (recommended to use natural language) + other additional tag elements

For example: This is a line drawing of A female character wearing robe in the rode, sun, cloud, trees.

(This is a line drawing of a female character wearing robe in the rode, sun, cloud, trees.)

Feel free to add elements on your own or use collected prompt words~

1. Its feature is to generate black and white line illustrations;

2. Remember to add prompt words, otherwise it will result in colors!!! Please do not include color-related terms in the descriptive words, as it will result in color images (but they still look pretty good).

3. Refer to specific LoRA effects by checking the sample images and the return image section!

Negative prompt word recommendations:

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 effect is achieved using the above-mentioned negative prompt words! The sample images are all generated using these negative prompt words.

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

Iteration steps: 30 (up to your mood)

Recommended size: 3:4 (feel free to try 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 of0.3-0.4, or directly use a redraw magnitude of 0.5 or above for card drawing.

<Important Notes>

There is a chance of hands and body, limbs problems in the generated images, multiple card drawings may be required!

- It is recommended to directly enlarge in high definition ×2 + 0.5 redraw card drawing~

- When the character is full body or small in proportion, facial collapse or blur may occur, please enable ADetailer and selectface_yolov8nfor repair!

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

Model Usage Disclaimer:

1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites or 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, using images for public posting on short video platforms or publications, etc.), please contact me through the platform (membership rights on the Lib platform prevail for members);

2. You are not allowed to directly sell images generated by this model unless you have made sufficient artistic modifications to the image to the extent that it can be fully considered your personal work in a legal sense. If you violate this clause, all legal consequences are your responsibility, and I shall not be held accountable (membership rights on the Lib platform prevail for members);

3. You are not allowed to use this model to intentionally create or share illegal or harmful content for dissemination. Please abide by ethical standards and use this model for positive and constructive purposes.